Cette page a été traduite par l'API Cloud Translation.
Switch to English

Minitaur du SAC

Copyright 2018 Les auteurs de TF-Agents.

Voir sur TensorFlow.org Exécuter dans Google Colab Afficher la source sur GitHub Télécharger le cahier

introduction

Cet exemple montre comment former un agent Soft Actor Critic sur l'environnement Minitaur à l'aide de la bibliothèque TF-Agents.

Si vous avez travaillé avec DQN Colab, cela devrait vous sembler très familier. Les changements notables incluent:

  • Changement de l'agent de DQN à SAC.
  • Formation sur Minitaur qui est un environnement beaucoup plus complexe que CartPole. L'environnement Minitaur vise à entraîner un robot quadrupède à avancer.
  • Nous n'utilisons pas de politique aléatoire pour effectuer une première collecte de données.

Si vous n'avez pas installé les dépendances suivantes, exécutez:

sudo apt-get install -y xvfb ffmpeg
pip install -q 'gym==0.10.11'
pip install -q 'imageio==2.4.0'
pip install -q matplotlib
pip install -q PILLOW
pip install -q tf-agents
pip install -q 'pybullet==2.4.2'



The following packages were automatically installed and are no longer required:
  dconf-gsettings-backend dconf-service dkms freeglut3 freeglut3-dev
  glib-networking glib-networking-common glib-networking-services
  gsettings-desktop-schemas libcairo-gobject2 libcolord2 libdconf1
  libegl1-mesa libepoxy0 libglu1-mesa libglu1-mesa-dev libgtk-3-0
  libgtk-3-common libice-dev libjansson4 libjson-glib-1.0-0
  libjson-glib-1.0-common libproxy1v5 librest-0.7-0 libsm-dev
  libsoup-gnome2.4-1 libsoup2.4-1 libxi-dev libxmu-dev libxmu-headers
  libxnvctrl0 libxt-dev linux-gcp-headers-5.0.0-1026
  linux-headers-5.0.0-1026-gcp linux-image-5.0.0-1026-gcp
  linux-modules-5.0.0-1026-gcp pkg-config policykit-1-gnome python3-xkit
  screen-resolution-extra xserver-xorg-core-hwe-18.04
Use 'sudo apt autoremove' to remove them.
The following additional packages will be installed:
  i965-va-driver libaacs0 libass9 libavc1394-0 libavcodec57 libavdevice57
  libavfilter6 libavformat57 libavresample3 libavutil55 libbdplus0 libbluray2
  libbs2b0 libcaca0 libcdio-cdda2 libcdio-paranoia2 libcdio17 libchromaprint1
  libcrystalhd3 libdc1394-22 libdrm-amdgpu1 libdrm-common libdrm-dev
  libdrm-intel1 libdrm-nouveau2 libdrm-radeon1 libdrm2 libfftw3-double3
  libflite1 libgme0 libgsm1 libiec61883-0 libjack-jackd2-0 libllvm10
  libmp3lame0 libmpg123-0 libmysofa0 libnorm1 libnuma1 libopenal-data
  libopenal1 libopenjp2-7 libopenmpt0 libopus0 libpgm-5.2-0 libpostproc54
  libraw1394-11 librubberband2 libsamplerate0 libsdl2-2.0-0 libshine3
  libsnappy1v5 libsndio6.1 libsodium23 libsoxr0 libspeex1 libssh-gcrypt-4
  libswresample2 libswscale4 libtheora0 libtwolame0 libva-drm2 libva-x11-2
  libva2 libvorbisfile3 libvpx5 libwavpack1 libwebpmux3 libx264-152
  libx265-146 libxss1 libxvidcore4 libzmq5 libzvbi-common libzvbi0
  mesa-va-drivers va-driver-all xserver-common
Suggested packages:
  ffmpeg-doc i965-va-driver-shaders libbluray-bdj firmware-crystalhd
  libfftw3-bin libfftw3-dev jackd2 libportaudio2 opus-tools libraw1394-doc
  sndiod speex
Recommended packages:
  xfonts-base
The following NEW packages will be installed:
  ffmpeg i965-va-driver libaacs0 libass9 libavc1394-0 libavcodec57
  libavdevice57 libavfilter6 libavformat57 libavresample3 libavutil55
  libbdplus0 libbluray2 libbs2b0 libcaca0 libcdio-cdda2 libcdio-paranoia2
  libcdio17 libchromaprint1 libcrystalhd3 libdc1394-22 libfftw3-double3
  libflite1 libgme0 libgsm1 libiec61883-0 libjack-jackd2-0 libllvm10
  libmp3lame0 libmpg123-0 libmysofa0 libnorm1 libnuma1 libopenal-data
  libopenal1 libopenjp2-7 libopenmpt0 libopus0 libpgm-5.2-0 libpostproc54
  libraw1394-11 librubberband2 libsamplerate0 libsdl2-2.0-0 libshine3
  libsnappy1v5 libsndio6.1 libsodium23 libsoxr0 libspeex1 libssh-gcrypt-4
  libswresample2 libswscale4 libtheora0 libtwolame0 libva-drm2 libva-x11-2
  libva2 libvorbisfile3 libvpx5 libwavpack1 libwebpmux3 libx264-152
  libx265-146 libxss1 libxvidcore4 libzmq5 libzvbi-common libzvbi0
  mesa-va-drivers va-driver-all xvfb
The following packages will be upgraded:
  libdrm-amdgpu1 libdrm-common libdrm-dev libdrm-intel1 libdrm-nouveau2
  libdrm-radeon1 libdrm2 xserver-common
8 upgraded, 72 newly installed, 0 to remove and 85 not upgraded.
Need to get 50.5 MB of archives.
After this operation, 199 MB of additional disk space will be used.
Get:1 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libxss1 amd64 1:1.2.2-1 [8582 B]
Get:2 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libdrm-common all 2.4.101-2~18.04.1 [5560 B]
Get:3 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libdrm-dev amd64 2.4.101-2~18.04.1 [126 kB]
Get:4 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libdrm-intel1 amd64 2.4.101-2~18.04.1 [60.0 kB]
Get:5 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libdrm-radeon1 amd64 2.4.101-2~18.04.1 [21.7 kB]
Get:6 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libdrm-nouveau2 amd64 2.4.101-2~18.04.1 [16.5 kB]
Get:7 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libdrm-amdgpu1 amd64 2.4.101-2~18.04.1 [18.2 kB]
Get:8 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libdrm2 amd64 2.4.101-2~18.04.1 [32.3 kB]
Get:9 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libnuma1 amd64 2.0.11-2.1ubuntu0.1 [22.0 kB]
Get:10 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libva2 amd64 2.1.0-3 [47.6 kB]
Get:11 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libva-drm2 amd64 2.1.0-3 [6880 B]
Get:12 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libva-x11-2 amd64 2.1.0-3 [11.5 kB]
Get:13 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libavutil55 amd64 7:3.4.8-0ubuntu0.2 [190 kB]
Get:14 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libcrystalhd3 amd64 1:0.0~git20110715.fdd2f19-12 [45.8 kB]
Get:15 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libgsm1 amd64 1.0.13-4build1 [22.4 kB]
Get:16 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libmp3lame0 amd64 3.100-2 [136 kB]
Get:17 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libopenjp2-7 amd64 2.3.0-2build0.18.04.1 [145 kB]
Get:18 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libopus0 amd64 1.1.2-1ubuntu1 [159 kB]
Get:19 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libshine3 amd64 3.1.1-1 [22.9 kB]
Get:20 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libsnappy1v5 amd64 1.1.7-1 [16.0 kB]
Get:21 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libspeex1 amd64 1.2~rc1.2-1ubuntu2 [52.1 kB]
Get:22 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libsoxr0 amd64 0.1.2-3 [65.9 kB]
Get:23 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libswresample2 amd64 7:3.4.8-0ubuntu0.2 [55.2 kB]
Get:24 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libtheora0 amd64 1.1.1+dfsg.1-14 [170 kB]
Get:25 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libtwolame0 amd64 0.3.13-3 [46.7 kB]
Get:26 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libvpx5 amd64 1.7.0-3ubuntu0.18.04.1 [796 kB]
Get:27 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libwavpack1 amd64 5.1.0-2ubuntu1.4 [76.6 kB]
Get:28 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libwebpmux3 amd64 0.6.1-2 [19.6 kB]
Get:29 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libx264-152 amd64 2:0.152.2854+gite9a5903-2 [609 kB]
Get:30 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libx265-146 amd64 2.6-3 [1026 kB]
Get:31 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libxvidcore4 amd64 2:1.3.5-1 [200 kB]
Get:32 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libzvbi-common all 0.2.35-13 [32.1 kB]
Get:33 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libzvbi0 amd64 0.2.35-13 [235 kB]
Get:34 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libavcodec57 amd64 7:3.4.8-0ubuntu0.2 [4595 kB]
Get:35 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libraw1394-11 amd64 2.1.2-1 [30.7 kB]
Get:36 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libavc1394-0 amd64 0.5.4-4build1 [16.1 kB]
Get:37 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libass9 amd64 1:0.14.0-1 [88.2 kB]
Get:38 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libbluray2 amd64 1:1.0.2-3 [141 kB]
Get:39 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libchromaprint1 amd64 1.4.3-1 [36.8 kB]
Get:40 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libgme0 amd64 0.6.2-1 [121 kB]
Get:41 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libmpg123-0 amd64 1.25.10-1 [125 kB]
Get:42 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libvorbisfile3 amd64 1.3.5-4.2 [16.0 kB]
Get:43 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libopenmpt0 amd64 0.3.6-1 [561 kB]
Get:44 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libssh-gcrypt-4 amd64 0.8.0~20170825.94fa1e38-1ubuntu0.7 [172 kB]
Get:45 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libavformat57 amd64 7:3.4.8-0ubuntu0.2 [953 kB]
Get:46 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libavresample3 amd64 7:3.4.8-0ubuntu0.2 [52.6 kB]
Get:47 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libbs2b0 amd64 3.1.0+dfsg-2.2 [10.5 kB]
Get:48 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libflite1 amd64 2.1-release-1 [12.8 MB]
Get:49 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libmysofa0 amd64 0.6~dfsg0-2ubuntu0.18.04.1 [38.1 kB]
Get:50 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libpostproc54 amd64 7:3.4.8-0ubuntu0.2 [50.3 kB]
Get:51 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libfftw3-double3 amd64 3.3.7-1 [735 kB]
Get:52 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libsamplerate0 amd64 0.1.9-1 [938 kB]
Get:53 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 librubberband2 amd64 1.8.1-7ubuntu2 [86.7 kB]
Get:54 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libswscale4 amd64 7:3.4.8-0ubuntu0.2 [150 kB]
Get:55 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libnorm1 amd64 1.5r6+dfsg1-6 [224 kB]
Get:56 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libpgm-5.2-0 amd64 5.2.122~dfsg-2 [157 kB]
Get:57 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libsodium23 amd64 1.0.16-2 [143 kB]
Get:58 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libzmq5 amd64 4.2.5-1ubuntu0.2 [221 kB]
Get:59 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libavfilter6 amd64 7:3.4.8-0ubuntu0.2 [874 kB]
Get:60 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libcaca0 amd64 0.99.beta19-2ubuntu0.18.04.1 [203 kB]
Get:61 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libcdio17 amd64 1.0.0-2ubuntu2 [58.8 kB]
Get:62 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libcdio-cdda2 amd64 10.2+0.94+2-2build1 [17.7 kB]
Get:63 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libcdio-paranoia2 amd64 10.2+0.94+2-2build1 [17.2 kB]
Get:64 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libdc1394-22 amd64 2.2.5-1 [77.5 kB]
Get:65 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libiec61883-0 amd64 1.2.0-2 [23.5 kB]
Get:66 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/main amd64 libjack-jackd2-0 amd64 1.9.12~dfsg-2 [263 kB]
Get:67 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libopenal-data all 1:1.18.2-2 [102 kB]
Get:68 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libsndio6.1 amd64 1.1.0-3 [23.4 kB]
Get:69 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libopenal1 amd64 1:1.18.2-2 [266 kB]
Get:70 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libsdl2-2.0-0 amd64 2.0.8+dfsg1-1ubuntu1.18.04.4 [382 kB]
Get:71 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 libavdevice57 amd64 7:3.4.8-0ubuntu0.2 [74.9 kB]
Get:72 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 ffmpeg amd64 7:3.4.8-0ubuntu0.2 [1587 kB]
Get:73 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libaacs0 amd64 0.9.0-1 [51.4 kB]
Get:74 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 libbdplus0 amd64 0.1.2-2 [46.6 kB]
Get:75 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 libllvm10 amd64 1:10.0.0-4ubuntu1~18.04.2 [15.4 MB]
Get:76 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 mesa-va-drivers amd64 20.0.8-0ubuntu1~18.04.1 [2376 kB]
Get:77 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 i965-va-driver amd64 2.1.0-0ubuntu1 [925 kB]
Get:78 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic/universe amd64 va-driver-all amd64 2.1.0-3 [4376 B]
Get:79 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/main amd64 xserver-common all 2:1.19.6-1ubuntu4.4 [27.3 kB]
Get:80 http://asia-east1.gce.archive.ubuntu.com/ubuntu bionic-updates/universe amd64 xvfb amd64 2:1.19.6-1ubuntu4.4 [784 kB]
Fetched 50.5 MB in 10s (5182 kB/s)
Extracting templates from packages: 100%
Selecting previously unselected package libxss1:amd64.
(Reading database ... 225433 files and directories currently installed.)
Preparing to unpack .../00-libxss1_1%3a1.2.2-1_amd64.deb ...
Unpacking libxss1:amd64 (1:1.2.2-1) ...
Preparing to unpack .../01-libdrm-common_2.4.101-2~18.04.1_all.deb ...
Unpacking libdrm-common (2.4.101-2~18.04.1) over (2.4.99-1ubuntu1~18.04.2) ...
Preparing to unpack .../02-libdrm-dev_2.4.101-2~18.04.1_amd64.deb ...
Unpacking libdrm-dev:amd64 (2.4.101-2~18.04.1) over (2.4.99-1ubuntu1~18.04.2) ...
Preparing to unpack .../03-libdrm-intel1_2.4.101-2~18.04.1_amd64.deb ...
Unpacking libdrm-intel1:amd64 (2.4.101-2~18.04.1) over (2.4.99-1ubuntu1~18.04.2) ...
Preparing to unpack .../04-libdrm-radeon1_2.4.101-2~18.04.1_amd64.deb ...
Unpacking libdrm-radeon1:amd64 (2.4.101-2~18.04.1) over (2.4.99-1ubuntu1~18.04.2) ...
Preparing to unpack .../05-libdrm-nouveau2_2.4.101-2~18.04.1_amd64.deb ...
Unpacking libdrm-nouveau2:amd64 (2.4.101-2~18.04.1) over (2.4.99-1ubuntu1~18.04.2) ...
Preparing to unpack .../06-libdrm-amdgpu1_2.4.101-2~18.04.1_amd64.deb ...
Unpacking libdrm-amdgpu1:amd64 (2.4.101-2~18.04.1) over (2.4.99-1ubuntu1~18.04.2) ...
Preparing to unpack .../07-libdrm2_2.4.101-2~18.04.1_amd64.deb ...
Unpacking libdrm2:amd64 (2.4.101-2~18.04.1) over (2.4.99-1ubuntu1~18.04.2) ...
Selecting previously unselected package libnuma1:amd64.
Preparing to unpack .../08-libnuma1_2.0.11-2.1ubuntu0.1_amd64.deb ...
Unpacking libnuma1:amd64 (2.0.11-2.1ubuntu0.1) ...
Selecting previously unselected package libva2:amd64.
Preparing to unpack .../09-libva2_2.1.0-3_amd64.deb ...
Unpacking libva2:amd64 (2.1.0-3) ...
Selecting previously unselected package libva-drm2:amd64.
Preparing to unpack .../10-libva-drm2_2.1.0-3_amd64.deb ...
Unpacking libva-drm2:amd64 (2.1.0-3) ...
Selecting previously unselected package libva-x11-2:amd64.
Preparing to unpack .../11-libva-x11-2_2.1.0-3_amd64.deb ...
Unpacking libva-x11-2:amd64 (2.1.0-3) ...
Selecting previously unselected package libavutil55:amd64.
Preparing to unpack .../12-libavutil55_7%3a3.4.8-0ubuntu0.2_amd64.deb ...
Unpacking libavutil55:amd64 (7:3.4.8-0ubuntu0.2) ...
Selecting previously unselected package libcrystalhd3:amd64.
Preparing to unpack .../13-libcrystalhd3_1%3a0.0~git20110715.fdd2f19-12_amd64.deb ...
Unpacking libcrystalhd3:amd64 (1:0.0~git20110715.fdd2f19-12) ...
Selecting previously unselected package libgsm1:amd64.
Preparing to unpack .../14-libgsm1_1.0.13-4build1_amd64.deb ...
Unpacking libgsm1:amd64 (1.0.13-4build1) ...
Selecting previously unselected package libmp3lame0:amd64.
Preparing to unpack .../15-libmp3lame0_3.100-2_amd64.deb ...
Unpacking libmp3lame0:amd64 (3.100-2) ...
Selecting previously unselected package libopenjp2-7:amd64.
Preparing to unpack .../16-libopenjp2-7_2.3.0-2build0.18.04.1_amd64.deb ...
Unpacking libopenjp2-7:amd64 (2.3.0-2build0.18.04.1) ...
Selecting previously unselected package libopus0:amd64.
Preparing to unpack .../17-libopus0_1.1.2-1ubuntu1_amd64.deb ...
Unpacking libopus0:amd64 (1.1.2-1ubuntu1) ...
Selecting previously unselected package libshine3:amd64.
Preparing to unpack .../18-libshine3_3.1.1-1_amd64.deb ...
Unpacking libshine3:amd64 (3.1.1-1) ...
Selecting previously unselected package libsnappy1v5:amd64.
Preparing to unpack .../19-libsnappy1v5_1.1.7-1_amd64.deb ...
Unpacking libsnappy1v5:amd64 (1.1.7-1) ...
Selecting previously unselected package libspeex1:amd64.
Preparing to unpack .../20-libspeex1_1.2~rc1.2-1ubuntu2_amd64.deb ...
Unpacking libspeex1:amd64 (1.2~rc1.2-1ubuntu2) ...
Selecting previously unselected package libsoxr0:amd64.
Preparing to unpack .../21-libsoxr0_0.1.2-3_amd64.deb ...
Unpacking libsoxr0:amd64 (0.1.2-3) ...
Selecting previously unselected package libswresample2:amd64.
Preparing to unpack .../22-libswresample2_7%3a3.4.8-0ubuntu0.2_amd64.deb ...
Unpacking libswresample2:amd64 (7:3.4.8-0ubuntu0.2) ...
Selecting previously unselected package libtheora0:amd64.
Preparing to unpack .../23-libtheora0_1.1.1+dfsg.1-14_amd64.deb ...
Unpacking libtheora0:amd64 (1.1.1+dfsg.1-14) ...
Selecting previously unselected package libtwolame0:amd64.
Preparing to unpack .../24-libtwolame0_0.3.13-3_amd64.deb ...
Unpacking libtwolame0:amd64 (0.3.13-3) ...
Selecting previously unselected package libvpx5:amd64.
Preparing to unpack .../25-libvpx5_1.7.0-3ubuntu0.18.04.1_amd64.deb ...
Unpacking libvpx5:amd64 (1.7.0-3ubuntu0.18.04.1) ...
Selecting previously unselected package libwavpack1:amd64.
Preparing to unpack .../26-libwavpack1_5.1.0-2ubuntu1.4_amd64.deb ...
Unpacking libwavpack1:amd64 (5.1.0-2ubuntu1.4) ...
Selecting previously unselected package libwebpmux3:amd64.
Preparing to unpack .../27-libwebpmux3_0.6.1-2_amd64.deb ...
Unpacking libwebpmux3:amd64 (0.6.1-2) ...
Selecting previously unselected package libx264-152:amd64.
Preparing to unpack .../28-libx264-152_2%3a0.152.2854+gite9a5903-2_amd64.deb ...
Unpacking libx264-152:amd64 (2:0.152.2854+gite9a5903-2) ...
Selecting previously unselected package libx265-146:amd64.
Preparing to unpack .../29-libx265-146_2.6-3_amd64.deb ...
Unpacking libx265-146:amd64 (2.6-3) ...
Selecting previously unselected package libxvidcore4:amd64.
Preparing to unpack .../30-libxvidcore4_2%3a1.3.5-1_amd64.deb ...
Unpacking libxvidcore4:amd64 (2:1.3.5-1) ...
Selecting previously unselected package libzvbi-common.
Preparing to unpack .../31-libzvbi-common_0.2.35-13_all.deb ...
Unpacking libzvbi-common (0.2.35-13) ...
Selecting previously unselected package libzvbi0:amd64.
Preparing to unpack .../32-libzvbi0_0.2.35-13_amd64.deb ...
Unpacking libzvbi0:amd64 (0.2.35-13) ...
Selecting previously unselected package libavcodec57:amd64.
Preparing to unpack .../33-libavcodec57_7%3a3.4.8-0ubuntu0.2_amd64.deb ...
Unpacking libavcodec57:amd64 (7:3.4.8-0ubuntu0.2) ...
Selecting previously unselected package libraw1394-11:amd64.
Preparing to unpack .../34-libraw1394-11_2.1.2-1_amd64.deb ...
Unpacking libraw1394-11:amd64 (2.1.2-1) ...
Selecting previously unselected package libavc1394-0:amd64.
Preparing to unpack .../35-libavc1394-0_0.5.4-4build1_amd64.deb ...
Unpacking libavc1394-0:amd64 (0.5.4-4build1) ...
Selecting previously unselected package libass9:amd64.
Preparing to unpack .../36-libass9_1%3a0.14.0-1_amd64.deb ...
Unpacking libass9:amd64 (1:0.14.0-1) ...
Selecting previously unselected package libbluray2:amd64.
Preparing to unpack .../37-libbluray2_1%3a1.0.2-3_amd64.deb ...
Unpacking libbluray2:amd64 (1:1.0.2-3) ...
Selecting previously unselected package libchromaprint1:amd64.
Preparing to unpack .../38-libchromaprint1_1.4.3-1_amd64.deb ...
Unpacking libchromaprint1:amd64 (1.4.3-1) ...
Selecting previously unselected package libgme0:amd64.
Preparing to unpack .../39-libgme0_0.6.2-1_amd64.deb ...
Unpacking libgme0:amd64 (0.6.2-1) ...
Selecting previously unselected package libmpg123-0:amd64.
Preparing to unpack .../40-libmpg123-0_1.25.10-1_amd64.deb ...
Unpacking libmpg123-0:amd64 (1.25.10-1) ...
Selecting previously unselected package libvorbisfile3:amd64.
Preparing to unpack .../41-libvorbisfile3_1.3.5-4.2_amd64.deb ...
Unpacking libvorbisfile3:amd64 (1.3.5-4.2) ...
Selecting previously unselected package libopenmpt0:amd64.
Preparing to unpack .../42-libopenmpt0_0.3.6-1_amd64.deb ...
Unpacking libopenmpt0:amd64 (0.3.6-1) ...
Selecting previously unselected package libssh-gcrypt-4:amd64.
Preparing to unpack .../43-libssh-gcrypt-4_0.8.0~20170825.94fa1e38-1ubuntu0.7_amd64.deb ...
Unpacking libssh-gcrypt-4:amd64 (0.8.0~20170825.94fa1e38-1ubuntu0.7) ...
Selecting previously unselected package libavformat57:amd64.
Preparing to unpack .../44-libavformat57_7%3a3.4.8-0ubuntu0.2_amd64.deb ...
Unpacking libavformat57:amd64 (7:3.4.8-0ubuntu0.2) ...
Selecting previously unselected package libavresample3:amd64.
Preparing to unpack .../45-libavresample3_7%3a3.4.8-0ubuntu0.2_amd64.deb ...
Unpacking libavresample3:amd64 (7:3.4.8-0ubuntu0.2) ...
Selecting previously unselected package libbs2b0:amd64.
Preparing to unpack .../46-libbs2b0_3.1.0+dfsg-2.2_amd64.deb ...
Unpacking libbs2b0:amd64 (3.1.0+dfsg-2.2) ...
Selecting previously unselected package libflite1:amd64.
Preparing to unpack .../47-libflite1_2.1-release-1_amd64.deb ...
Unpacking libflite1:amd64 (2.1-release-1) ...
Selecting previously unselected package libmysofa0:amd64.
Preparing to unpack .../48-libmysofa0_0.6~dfsg0-2ubuntu0.18.04.1_amd64.deb ...
Unpacking libmysofa0:amd64 (0.6~dfsg0-2ubuntu0.18.04.1) ...
Selecting previously unselected package libpostproc54:amd64.
Preparing to unpack .../49-libpostproc54_7%3a3.4.8-0ubuntu0.2_amd64.deb ...
Unpacking libpostproc54:amd64 (7:3.4.8-0ubuntu0.2) ...
Selecting previously unselected package libfftw3-double3:amd64.
Preparing to unpack .../50-libfftw3-double3_3.3.7-1_amd64.deb ...
Unpacking libfftw3-double3:amd64 (3.3.7-1) ...
Selecting previously unselected package libsamplerate0:amd64.
Preparing to unpack .../51-libsamplerate0_0.1.9-1_amd64.deb ...
Unpacking libsamplerate0:amd64 (0.1.9-1) ...
Selecting previously unselected package librubberband2:amd64.
Preparing to unpack .../52-librubberband2_1.8.1-7ubuntu2_amd64.deb ...
Unpacking librubberband2:amd64 (1.8.1-7ubuntu2) ...
Selecting previously unselected package libswscale4:amd64.
Preparing to unpack .../53-libswscale4_7%3a3.4.8-0ubuntu0.2_amd64.deb ...
Unpacking libswscale4:amd64 (7:3.4.8-0ubuntu0.2) ...
Selecting previously unselected package libnorm1:amd64.
Preparing to unpack .../54-libnorm1_1.5r6+dfsg1-6_amd64.deb ...
Unpacking libnorm1:amd64 (1.5r6+dfsg1-6) ...
Selecting previously unselected package libpgm-5.2-0:amd64.
Preparing to unpack .../55-libpgm-5.2-0_5.2.122~dfsg-2_amd64.deb ...
Unpacking libpgm-5.2-0:amd64 (5.2.122~dfsg-2) ...
Selecting previously unselected package libsodium23:amd64.
Preparing to unpack .../56-libsodium23_1.0.16-2_amd64.deb ...
Unpacking libsodium23:amd64 (1.0.16-2) ...
Selecting previously unselected package libzmq5:amd64.
Preparing to unpack .../57-libzmq5_4.2.5-1ubuntu0.2_amd64.deb ...
Unpacking libzmq5:amd64 (4.2.5-1ubuntu0.2) ...
Selecting previously unselected package libavfilter6:amd64.
Preparing to unpack .../58-libavfilter6_7%3a3.4.8-0ubuntu0.2_amd64.deb ...
Unpacking libavfilter6:amd64 (7:3.4.8-0ubuntu0.2) ...
Selecting previously unselected package libcaca0:amd64.
Preparing to unpack .../59-libcaca0_0.99.beta19-2ubuntu0.18.04.1_amd64.deb ...
Unpacking libcaca0:amd64 (0.99.beta19-2ubuntu0.18.04.1) ...
Selecting previously unselected package libcdio17:amd64.
Preparing to unpack .../60-libcdio17_1.0.0-2ubuntu2_amd64.deb ...
Unpacking libcdio17:amd64 (1.0.0-2ubuntu2) ...
Selecting previously unselected package libcdio-cdda2:amd64.
Preparing to unpack .../61-libcdio-cdda2_10.2+0.94+2-2build1_amd64.deb ...
Unpacking libcdio-cdda2:amd64 (10.2+0.94+2-2build1) ...
Selecting previously unselected package libcdio-paranoia2:amd64.
Preparing to unpack .../62-libcdio-paranoia2_10.2+0.94+2-2build1_amd64.deb ...
Unpacking libcdio-paranoia2:amd64 (10.2+0.94+2-2build1) ...
Selecting previously unselected package libdc1394-22:amd64.
Preparing to unpack .../63-libdc1394-22_2.2.5-1_amd64.deb ...
Unpacking libdc1394-22:amd64 (2.2.5-1) ...
Selecting previously unselected package libiec61883-0:amd64.
Preparing to unpack .../64-libiec61883-0_1.2.0-2_amd64.deb ...
Unpacking libiec61883-0:amd64 (1.2.0-2) ...
Selecting previously unselected package libjack-jackd2-0:amd64.
Preparing to unpack .../65-libjack-jackd2-0_1.9.12~dfsg-2_amd64.deb ...
Unpacking libjack-jackd2-0:amd64 (1.9.12~dfsg-2) ...
Selecting previously unselected package libopenal-data.
Preparing to unpack .../66-libopenal-data_1%3a1.18.2-2_all.deb ...
Unpacking libopenal-data (1:1.18.2-2) ...
Selecting previously unselected package libsndio6.1:amd64.
Preparing to unpack .../67-libsndio6.1_1.1.0-3_amd64.deb ...
Unpacking libsndio6.1:amd64 (1.1.0-3) ...
Selecting previously unselected package libopenal1:amd64.
Preparing to unpack .../68-libopenal1_1%3a1.18.2-2_amd64.deb ...
Unpacking libopenal1:amd64 (1:1.18.2-2) ...
Selecting previously unselected package libsdl2-2.0-0:amd64.
Preparing to unpack .../69-libsdl2-2.0-0_2.0.8+dfsg1-1ubuntu1.18.04.4_amd64.deb ...
Unpacking libsdl2-2.0-0:amd64 (2.0.8+dfsg1-1ubuntu1.18.04.4) ...
Selecting previously unselected package libavdevice57:amd64.
Preparing to unpack .../70-libavdevice57_7%3a3.4.8-0ubuntu0.2_amd64.deb ...
Unpacking libavdevice57:amd64 (7:3.4.8-0ubuntu0.2) ...
Selecting previously unselected package ffmpeg.
Preparing to unpack .../71-ffmpeg_7%3a3.4.8-0ubuntu0.2_amd64.deb ...
Unpacking ffmpeg (7:3.4.8-0ubuntu0.2) ...
Selecting previously unselected package libaacs0:amd64.
Preparing to unpack .../72-libaacs0_0.9.0-1_amd64.deb ...
Unpacking libaacs0:amd64 (0.9.0-1) ...
Selecting previously unselected package libbdplus0:amd64.
Preparing to unpack .../73-libbdplus0_0.1.2-2_amd64.deb ...
Unpacking libbdplus0:amd64 (0.1.2-2) ...
Selecting previously unselected package libllvm10:amd64.
Preparing to unpack .../74-libllvm10_1%3a10.0.0-4ubuntu1~18.04.2_amd64.deb ...
Unpacking libllvm10:amd64 (1:10.0.0-4ubuntu1~18.04.2) ...
Selecting previously unselected package mesa-va-drivers:amd64.
Preparing to unpack .../75-mesa-va-drivers_20.0.8-0ubuntu1~18.04.1_amd64.deb ...
Unpacking mesa-va-drivers:amd64 (20.0.8-0ubuntu1~18.04.1) ...
Selecting previously unselected package i965-va-driver:amd64.
Preparing to unpack .../76-i965-va-driver_2.1.0-0ubuntu1_amd64.deb ...
Unpacking i965-va-driver:amd64 (2.1.0-0ubuntu1) ...
Selecting previously unselected package va-driver-all:amd64.
Preparing to unpack .../77-va-driver-all_2.1.0-3_amd64.deb ...
Unpacking va-driver-all:amd64 (2.1.0-3) ...
Preparing to unpack .../78-xserver-common_2%3a1.19.6-1ubuntu4.4_all.deb ...
Unpacking xserver-common (2:1.19.6-1ubuntu4.4) over (2:1.19.6-1ubuntu4.3) ...
Selecting previously unselected package xvfb.
Preparing to unpack .../79-xvfb_2%3a1.19.6-1ubuntu4.4_amd64.deb ...
Unpacking xvfb (2:1.19.6-1ubuntu4.4) ...
Setting up libvorbisfile3:amd64 (1.3.5-4.2) ...
Setting up libpgm-5.2-0:amd64 (5.2.122~dfsg-2) ...
Setting up libtwolame0:amd64 (0.3.13-3) ...
Setting up libraw1394-11:amd64 (2.1.2-1) ...
Setting up libx264-152:amd64 (2:0.152.2854+gite9a5903-2) ...
Setting up xserver-common (2:1.19.6-1ubuntu4.4) ...
Setting up libopenjp2-7:amd64 (2.3.0-2build0.18.04.1) ...
Setting up libllvm10:amd64 (1:10.0.0-4ubuntu1~18.04.2) ...
Setting up libwavpack1:amd64 (5.1.0-2ubuntu1.4) ...
Setting up xvfb (2:1.19.6-1ubuntu4.4) ...
Setting up libaacs0:amd64 (0.9.0-1) ...
Setting up libnuma1:amd64 (2.0.11-2.1ubuntu0.1) ...
Setting up libflite1:amd64 (2.1-release-1) ...
Setting up libsoxr0:amd64 (0.1.2-3) ...
Setting up libssh-gcrypt-4:amd64 (0.8.0~20170825.94fa1e38-1ubuntu0.7) ...
Setting up libxss1:amd64 (1:1.2.2-1) ...
Setting up libass9:amd64 (1:0.14.0-1) ...
Setting up libbluray2:amd64 (1:1.0.2-3) ...
Setting up libdc1394-22:amd64 (2.2.5-1) ...
Setting up libshine3:amd64 (3.1.1-1) ...
Setting up libva2:amd64 (2.1.0-3) ...
Setting up libiec61883-0:amd64 (1.2.0-2) ...
Setting up libspeex1:amd64 (1.2~rc1.2-1ubuntu2) ...
Setting up libfftw3-double3:amd64 (3.3.7-1) ...
Setting up libxvidcore4:amd64 (2:1.3.5-1) ...
Setting up libopus0:amd64 (1.1.2-1ubuntu1) ...
Setting up libx265-146:amd64 (2.6-3) ...
Setting up libopenal-data (1:1.18.2-2) ...
Setting up libdrm-common (2.4.101-2~18.04.1) ...
Setting up libbs2b0:amd64 (3.1.0+dfsg-2.2) ...
Setting up libnorm1:amd64 (1.5r6+dfsg1-6) ...
Setting up libsodium23:amd64 (1.0.16-2) ...
Setting up libmp3lame0:amd64 (3.100-2) ...
Setting up libcrystalhd3:amd64 (1:0.0~git20110715.fdd2f19-12) ...
Setting up libwebpmux3:amd64 (0.6.1-2) ...
Setting up libsnappy1v5:amd64 (1.1.7-1) ...
Setting up libavc1394-0:amd64 (0.5.4-4build1) ...
Setting up libzvbi-common (0.2.35-13) ...
Setting up libvpx5:amd64 (1.7.0-3ubuntu0.18.04.1) ...
Setting up libgme0:amd64 (0.6.2-1) ...
Setting up libbdplus0:amd64 (0.1.2-2) ...
Setting up libzvbi0:amd64 (0.2.35-13) ...
Setting up libcaca0:amd64 (0.99.beta19-2ubuntu0.18.04.1) ...
Setting up libsamplerate0:amd64 (0.1.9-1) ...
Setting up libsndio6.1:amd64 (1.1.0-3) ...
Setting up libtheora0:amd64 (1.1.1+dfsg.1-14) ...
Setting up libmpg123-0:amd64 (1.25.10-1) ...
Setting up libgsm1:amd64 (1.0.13-4build1) ...
Setting up libmysofa0:amd64 (0.6~dfsg0-2ubuntu0.18.04.1) ...
Setting up libcdio17:amd64 (1.0.0-2ubuntu2) ...
Setting up libzmq5:amd64 (4.2.5-1ubuntu0.2) ...
Setting up libopenmpt0:amd64 (0.3.6-1) ...
Setting up libcdio-cdda2:amd64 (10.2+0.94+2-2build1) ...
Setting up libdrm2:amd64 (2.4.101-2~18.04.1) ...
Setting up libdrm-intel1:amd64 (2.4.101-2~18.04.1) ...
Setting up librubberband2:amd64 (1.8.1-7ubuntu2) ...
Setting up libsdl2-2.0-0:amd64 (2.0.8+dfsg1-1ubuntu1.18.04.4) ...
Setting up libcdio-paranoia2:amd64 (10.2+0.94+2-2build1) ...
Setting up libva-drm2:amd64 (2.1.0-3) ...
Setting up libjack-jackd2-0:amd64 (1.9.12~dfsg-2) ...
Setting up libopenal1:amd64 (1:1.18.2-2) ...
Setting up libdrm-radeon1:amd64 (2.4.101-2~18.04.1) ...
Setting up libva-x11-2:amd64 (2.1.0-3) ...
Setting up libdrm-nouveau2:amd64 (2.4.101-2~18.04.1) ...
Setting up libavutil55:amd64 (7:3.4.8-0ubuntu0.2) ...
Setting up libdrm-amdgpu1:amd64 (2.4.101-2~18.04.1) ...
Setting up libdrm-dev:amd64 (2.4.101-2~18.04.1) ...
Setting up libswresample2:amd64 (7:3.4.8-0ubuntu0.2) ...
Setting up i965-va-driver:amd64 (2.1.0-0ubuntu1) ...
Setting up libswscale4:amd64 (7:3.4.8-0ubuntu0.2) ...
Setting up mesa-va-drivers:amd64 (20.0.8-0ubuntu1~18.04.1) ...
Setting up libpostproc54:amd64 (7:3.4.8-0ubuntu0.2) ...
Setting up libavresample3:amd64 (7:3.4.8-0ubuntu0.2) ...
Setting up libavcodec57:amd64 (7:3.4.8-0ubuntu0.2) ...
Setting up va-driver-all:amd64 (2.1.0-3) ...
Setting up libchromaprint1:amd64 (1.4.3-1) ...
Setting up libavformat57:amd64 (7:3.4.8-0ubuntu0.2) ...
Setting up libavfilter6:amd64 (7:3.4.8-0ubuntu0.2) ...
Setting up libavdevice57:amd64 (7:3.4.8-0ubuntu0.2) ...
Setting up ffmpeg (7:3.4.8-0ubuntu0.2) ...
Processing triggers for libc-bin (2.27-3ubuntu1.2) ...
Processing triggers for man-db (2.8.3-2ubuntu0.1) ...

Installer

Nous allons d'abord importer les différents outils dont nous avons besoin et nous assurer que nous activons le comportement TF-V2 car il est plus facile d'itérer en mode Eager dans tout le colab.

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import base64
import imageio
import IPython
import matplotlib
import matplotlib.pyplot as plt
import PIL.Image

import tensorflow as tf
tf.compat.v1.enable_v2_behavior()

from tf_agents.agents.ddpg import critic_network
from tf_agents.agents.sac import sac_agent
from tf_agents.drivers import dynamic_step_driver
from tf_agents.environments import suite_pybullet
from tf_agents.environments import tf_py_environment
from tf_agents.eval import metric_utils
from tf_agents.metrics import tf_metrics
from tf_agents.networks import actor_distribution_network
from tf_agents.networks import normal_projection_network
from tf_agents.policies import greedy_policy
from tf_agents.policies import random_tf_policy
from tf_agents.replay_buffers import tf_uniform_replay_buffer
from tf_agents.trajectories import trajectory
from tf_agents.utils import common

Hyperparamètres

env_name = "MinitaurBulletEnv-v0" # @param {type:"string"}

# use "num_iterations = 1e6" for better results,
# 1e5 is just so this doesn't take too long. 
num_iterations = 100000 # @param {type:"integer"}

initial_collect_steps = 10000 # @param {type:"integer"} 
collect_steps_per_iteration = 1 # @param {type:"integer"}
replay_buffer_capacity = 1000000 # @param {type:"integer"}

batch_size = 256 # @param {type:"integer"}

critic_learning_rate = 3e-4 # @param {type:"number"}
actor_learning_rate = 3e-4 # @param {type:"number"}
alpha_learning_rate = 3e-4 # @param {type:"number"}
target_update_tau = 0.005 # @param {type:"number"}
target_update_period = 1 # @param {type:"number"}
gamma = 0.99 # @param {type:"number"}
reward_scale_factor = 1.0 # @param {type:"number"}
gradient_clipping = None # @param

actor_fc_layer_params = (256, 256)
critic_joint_fc_layer_params = (256, 256)

log_interval = 5000 # @param {type:"integer"}

num_eval_episodes = 30 # @param {type:"integer"}
eval_interval = 10000 # @param {type:"integer"}

Environnement

Les environnements dans RL représentent la tâche ou le problème que nous essayons de résoudre. Les environnements standard peuvent être facilement créés dans TF-Agents à l'aide de suites . Nous avons différentes suites pour charger des environnements à partir de sources telles que OpenAI Gym, Atari, DM Control, etc., avec un nom d'environnement de chaîne.

Chargez maintenant l'environnement Minituar depuis la suite Pybullet.

env = suite_pybullet.load(env_name)
env.reset()
PIL.Image.fromarray(env.render())
current_dir=/tmpfs/src/tf_docs_env/lib/python3.6/site-packages/pybullet_envs/bullet
urdf_root=/tmpfs/src/tf_docs_env/lib/python3.6/site-packages/pybullet_data
options= 

/tmpfs/src/tf_docs_env/lib/python3.6/site-packages/gym/logger.py:30: UserWarning: WARN: gym.spaces.Box autodetected dtype as <class 'numpy.float32'>. Please provide explicit dtype.
  warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow'))

png

Dans cet environnement, le but est pour l'agent de former une politique qui contrôlera le robot Minitaur et le fera avancer aussi vite que possible. Les épisodes durent 1000 étapes et le retour sera la somme des récompenses tout au long de l'épisode.

Examinons les informations fournies par l'environnement comme une observation que la politique utilisera pour générer des actions .

print('Observation Spec:')
print(env.time_step_spec().observation)
print('Action Spec:')
print(env.action_spec())
Observation Spec:
BoundedArraySpec(shape=(28,), dtype=dtype('float32'), name='observation', minimum=[  -3.1515927   -3.1515927   -3.1515927   -3.1515927   -3.1515927
   -3.1515927   -3.1515927   -3.1515927 -167.72488   -167.72488
 -167.72488   -167.72488   -167.72488   -167.72488   -167.72488
 -167.72488     -5.71        -5.71        -5.71        -5.71
   -5.71        -5.71        -5.71        -5.71        -1.01
   -1.01        -1.01        -1.01     ], maximum=[  3.1515927   3.1515927   3.1515927   3.1515927   3.1515927   3.1515927
   3.1515927   3.1515927 167.72488   167.72488   167.72488   167.72488
 167.72488   167.72488   167.72488   167.72488     5.71        5.71
   5.71        5.71        5.71        5.71        5.71        5.71
   1.01        1.01        1.01        1.01     ])
Action Spec:
BoundedArraySpec(shape=(8,), dtype=dtype('float32'), name='action', minimum=-1.0, maximum=1.0)

Comme on peut le voir, l'observation est assez complexe. Nous recevons 28 valeurs représentant les angles, les vitesses et les couples pour tous les moteurs. En retour, l'environnement attend 8 valeurs pour les actions entre [-1, 1] . Ce sont les angles de moteur souhaités.

Habituellement, nous créons deux environnements: un pour la formation et un pour l'évaluation. La plupart des environnements sont écrits en python pur, mais ils peuvent être facilement convertis en TensorFlow à l'aide du wrapper TFPyEnvironment . L'API de l'environnement d'origine utilise des tableaux numpy, TFPyEnvironment convertit vers / depuis Tensors pour que vous puissiez interagir plus facilement avec les politiques et agents TensorFlow.

train_py_env = suite_pybullet.load(env_name)
eval_py_env = suite_pybullet.load(env_name)

train_env = tf_py_environment.TFPyEnvironment(train_py_env)
eval_env = tf_py_environment.TFPyEnvironment(eval_py_env)
urdf_root=/tmpfs/src/tf_docs_env/lib/python3.6/site-packages/pybullet_data
options= 
urdf_root=/tmpfs/src/tf_docs_env/lib/python3.6/site-packages/pybullet_data
options= 

Agent

Pour créer un agent SAC, nous devons d'abord créer les réseaux qu'il formera. SAC est un agent acteur-critique, nous aurons donc besoin de deux réseaux.

Le critique nous donnera des estimations de valeur pour Q(s,a) . Autrement dit, il recevra en entrée une observation et une action, et il nous donnera une estimation de la qualité de cette action pour l'état donné.

observation_spec = train_env.observation_spec()
action_spec = train_env.action_spec()
critic_net = critic_network.CriticNetwork(
    (observation_spec, action_spec),
    observation_fc_layer_params=None,
    action_fc_layer_params=None,
    joint_fc_layer_params=critic_joint_fc_layer_params)

Nous utiliserons cette critique pour former un réseau d' actor qui nous permettra de générer des actions à partir d'un constat.

L' ActorNetwork les paramètres d'une distribution normale. Cette distribution sera ensuite échantillonnée, conditionnée à l'observation actuelle, chaque fois que nous aurons besoin de générer des actions.

def normal_projection_net(action_spec,init_means_output_factor=0.1):
  return normal_projection_network.NormalProjectionNetwork(
      action_spec,
      mean_transform=None,
      state_dependent_std=True,
      init_means_output_factor=init_means_output_factor,
      std_transform=sac_agent.std_clip_transform,
      scale_distribution=True)


actor_net = actor_distribution_network.ActorDistributionNetwork(
    observation_spec,
    action_spec,
    fc_layer_params=actor_fc_layer_params,
    continuous_projection_net=normal_projection_net)

Avec ces réseaux à portée de main, nous pouvons maintenant instancier l'agent.

global_step = tf.compat.v1.train.get_or_create_global_step()
tf_agent = sac_agent.SacAgent(
    train_env.time_step_spec(),
    action_spec,
    actor_network=actor_net,
    critic_network=critic_net,
    actor_optimizer=tf.compat.v1.train.AdamOptimizer(
        learning_rate=actor_learning_rate),
    critic_optimizer=tf.compat.v1.train.AdamOptimizer(
        learning_rate=critic_learning_rate),
    alpha_optimizer=tf.compat.v1.train.AdamOptimizer(
        learning_rate=alpha_learning_rate),
    target_update_tau=target_update_tau,
    target_update_period=target_update_period,
    td_errors_loss_fn=tf.compat.v1.losses.mean_squared_error,
    gamma=gamma,
    reward_scale_factor=reward_scale_factor,
    gradient_clipping=gradient_clipping,
    train_step_counter=global_step)
tf_agent.initialize()

Stratégies

Dans TF-Agents, les politiques représentent la notion standard de politiques dans RL: un time_step donné produit une action ou une distribution sur les actions. La méthode principale est policy_step = policy.step(time_step)policy_step est un tuple nommé PolicyStep(action, state, info) . policy_step.action est l' action à appliquer à l'environnement, l' state représente l'état des politiques avec état (RNN) et les info peuvent contenir des informations auxiliaires telles que les probabilités de journalisation des actions.

Les agents contiennent deux stratégies: la stratégie principale (agent.policy) et la stratégie comportementale utilisée pour la collecte de données (agent.collect_policy). Pour l'évaluation / le déploiement, nous prenons l'action moyenne en enveloppant la stratégie principale avec GreedyPolicy ().

eval_policy = greedy_policy.GreedyPolicy(tf_agent.policy)
collect_policy = tf_agent.collect_policy

Mesures et évaluation

La mesure la plus couramment utilisée pour évaluer une politique est le rendement moyen. Le retour est la somme des récompenses obtenues lors de l'exécution d'une politique dans un environnement pour un épisode, et nous en moyenne généralement sur quelques épisodes. Nous pouvons calculer la métrique de retour moyenne comme suit.

def compute_avg_return(environment, policy, num_episodes=5):

  total_return = 0.0
  for _ in range(num_episodes):

    time_step = environment.reset()
    episode_return = 0.0

    while not time_step.is_last():
      action_step = policy.action(time_step)
      time_step = environment.step(action_step.action)
      episode_return += time_step.reward
    total_return += episode_return

  avg_return = total_return / num_episodes
  return avg_return.numpy()[0]


compute_avg_return(eval_env, eval_policy, num_eval_episodes)

# Please also see the metrics module for standard implementations of different
# metrics.
-0.020122046

Tampon de relecture

Afin de garder une trace des données collectées à partir de l'environnement, nous utiliserons le TFUniformReplayBuffer. Ce tampon de relecture est construit à l'aide de spécifications décrivant les tenseurs à stocker, qui peuvent être obtenues auprès de l'agent en utilisant tf_agent.collect_data_spec .

replay_buffer = tf_uniform_replay_buffer.TFUniformReplayBuffer(
    data_spec=tf_agent.collect_data_spec,
    batch_size=train_env.batch_size,
    max_length=replay_buffer_capacity)

Pour la plupart des agents, collect_data_spec est un tuple nommé Trajectory contenant l'observation, l'action, la récompense, etc.

Collecte de données

Nous allons maintenant créer un pilote pour collecter de l'expérience afin d'amorcer le tampon de relecture. Les chauffeurs nous fournissent un moyen simple de collecter n étapes ou épisodes sur un environnement en utilisant une politique spécifique.

initial_collect_driver = dynamic_step_driver.DynamicStepDriver(
        train_env,
        collect_policy,
        observers=[replay_buffer.add_batch],
        num_steps=initial_collect_steps)
initial_collect_driver.run()
WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tf_agents/drivers/dynamic_step_driver.py:203: calling while_loop_v2 (from tensorflow.python.ops.control_flow_ops) with back_prop=False is deprecated and will be removed in a future version.
Instructions for updating:
back_prop=False is deprecated. Consider using tf.stop_gradient instead.
Instead of:
results = tf.while_loop(c, b, vars, back_prop=False)
Use:
results = tf.nest.map_structure(tf.stop_gradient, tf.while_loop(c, b, vars))

(TimeStep(step_type=<tf.Tensor: shape=(1,), dtype=int32, numpy=array([1], dtype=int32)>, reward=<tf.Tensor: shape=(1,), dtype=float32, numpy=array([-0.00075403], dtype=float32)>, discount=<tf.Tensor: shape=(1,), dtype=float32, numpy=array([1.], dtype=float32)>, observation=<tf.Tensor: shape=(1, 28), dtype=float32, numpy=
 array([[  2.3280106 ,   2.2479935 ,   2.099398  ,   1.9307964 ,
           1.561656  ,   2.2268918 ,   1.4146138 ,   1.3288667 ,
         -12.17984   ,  14.122822  , -17.687569  ,   6.8371863 ,
           4.210765  , -23.897743  ,  12.569471  ,   4.3365436 ,
          -0.5463422 ,   0.61064804,  -5.7       ,   4.096758  ,
           0.8176498 ,  -5.7       ,   5.7       ,   5.7       ,
           0.1799443 ,  -0.03590513,   0.11489101,   0.97628427]],
       dtype=float32)>),
 ())

Afin d'échantillonner les données du tampon de relecture, nous allons créer un pipeline tf.data que nous pourrons alimenter l'agent pour une formation ultérieure. Nous pouvons spécifier sample_batch_size pour configurer le nombre d'éléments échantillonnés à partir du tampon de relecture. Nous pouvons également optimiser le pipeline de données à l'aide d'appels parallèles et de prélecture.

Afin de gagner de la place, nous ne stockons que l'observation actuelle dans chaque ligne du tampon de relecture. Mais comme l'agent SAC a besoin à la fois de l'observation actuelle et de l'observation suivante pour calculer la perte, nous échantillonnons toujours deux lignes adjacentes pour chaque élément du lot en définissant num_steps=2 .

# Dataset generates trajectories with shape [Bx2x...]
dataset = replay_buffer.as_dataset(
    num_parallel_calls=3, sample_batch_size=batch_size, num_steps=2).prefetch(3)

iterator = iter(dataset)
WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow/python/autograph/operators/control_flow.py:1004: ReplayBuffer.get_next (from tf_agents.replay_buffers.replay_buffer) is deprecated and will be removed in a future version.
Instructions for updating:
Use `as_dataset(..., single_deterministic_pass=False) instead.

Former l'agent

La boucle d'apprentissage implique à la fois la collecte de données de l'environnement et l'optimisation des réseaux de l'agent. En cours de route, nous évaluerons occasionnellement la politique de l'agent pour voir comment nous allons.

collect_driver = dynamic_step_driver.DynamicStepDriver(
    train_env,
    collect_policy,
    observers=[replay_buffer.add_batch],
    num_steps=collect_steps_per_iteration)

try:
  %%time
except:
  pass

# (Optional) Optimize by wrapping some of the code in a graph using TF function.
tf_agent.train = common.function(tf_agent.train)
collect_driver.run = common.function(collect_driver.run)

# Reset the train step
tf_agent.train_step_counter.assign(0)

# Evaluate the agent's policy once before training.
avg_return = compute_avg_return(eval_env, eval_policy, num_eval_episodes)
returns = [avg_return]

for _ in range(num_iterations):

  # Collect a few steps using collect_policy and save to the replay buffer.
  collect_driver.run()

  # Sample a batch of data from the buffer and update the agent's network.
  experience, unused_info = next(iterator)
  train_loss = tf_agent.train(experience)

  step = tf_agent.train_step_counter.numpy()

  if step % log_interval == 0:
    print('step = {0}: loss = {1}'.format(step, train_loss.loss))

  if step % eval_interval == 0:
    avg_return = compute_avg_return(eval_env, eval_policy, num_eval_episodes)
    print('step = {0}: Average Return = {1}'.format(step, avg_return))
    returns.append(avg_return)
WARNING:absl:Need to use a loss function that computes losses per sample, ex: replace losses.mean_squared_error with tf.math.squared_difference. Invalid value passed for `per_example_loss`. Expected a tensor tensor with at least rank 1, received: Tensor("critic_loss/add_1:0", shape=(), dtype=float32)
WARNING:absl:Need to use a loss function that computes losses per sample, ex: replace losses.mean_squared_error with tf.math.squared_difference. Invalid value passed for `per_example_loss`. Expected a tensor tensor with at least rank 1, received: Tensor("critic_loss/add_1:0", shape=(), dtype=float32)

step = 5000: loss = -51.00037384033203
step = 10000: loss = -33.40278244018555
step = 10000: Average Return = 0.23090466856956482
step = 15000: loss = -25.848711013793945
step = 20000: loss = -17.856319427490234
step = 20000: Average Return = -0.739188551902771
step = 25000: loss = -10.227678298950195
step = 30000: loss = -11.544439315795898
step = 30000: Average Return = -1.0969164371490479
step = 35000: loss = -4.284392356872559
step = 40000: loss = -1.6607131958007812
step = 40000: Average Return = 0.8357512354850769
step = 45000: loss = -0.4639418125152588
step = 50000: loss = -0.2797696590423584
step = 50000: Average Return = 0.006683715153485537
step = 55000: loss = 3.714784860610962
step = 60000: loss = -2.3239288330078125
step = 60000: Average Return = 0.03795448690652847
step = 65000: loss = -4.505060195922852
step = 70000: loss = 5.578963756561279
step = 70000: Average Return = 0.2851020097732544
step = 75000: loss = -4.925449371337891
step = 80000: loss = 0.15504467487335205
step = 80000: Average Return = 1.708200454711914
step = 85000: loss = 9.208975791931152
step = 90000: loss = 1.5110950469970703
step = 90000: Average Return = 1.0524197816848755
step = 95000: loss = -2.2562344074249268
step = 100000: loss = -0.9396060705184937
step = 100000: Average Return = 0.3255569636821747

Visualisation

Parcelles

Nous pouvons tracer le rendement moyen par rapport aux étapes globales pour voir les performances de notre agent. Dans Minitaur , la fonction de récompense est basée sur la distance parcourue par le minitaur en 1000 pas et pénalise la dépense énergétique.



steps = range(0, num_iterations + 1, eval_interval)
plt.plot(steps, returns)
plt.ylabel('Average Return')
plt.xlabel('Step')
plt.ylim()
(-1.237172281742096, 1.8484562993049622)

png

Vidéos

Il est utile de visualiser les performances d'un agent en rendant l'environnement à chaque étape. Avant de faire cela, créons d'abord une fonction pour intégrer des vidéos dans ce colab.

def embed_mp4(filename):
  """Embeds an mp4 file in the notebook."""
  video = open(filename,'rb').read()
  b64 = base64.b64encode(video)
  tag = '''
  <video width="640" height="480" controls>
    <source src="data:video/mp4;base64,{0}" type="video/mp4">
  Your browser does not support the video tag.
  </video>'''.format(b64.decode())

  return IPython.display.HTML(tag)

Le code suivant visualise la stratégie de l'agent pour quelques épisodes:

num_episodes = 3
video_filename = 'sac_minitaur.mp4'
with imageio.get_writer(video_filename, fps=60) as video:
  for _ in range(num_episodes):
    time_step = eval_env.reset()
    video.append_data(eval_py_env.render())
    while not time_step.is_last():
      action_step = tf_agent.policy.action(time_step)
      time_step = eval_env.step(action_step.action)
      video.append_data(eval_py_env.render())

embed_mp4(video_filename)