Reinforcement Learning

Play a board game against an agent, which is trained using reinforcement learning and deployed with TensorFlow Lite.

Get started

If you are new to TensorFlow Lite and are working with Android, we recommend exploring the following example application that can help you get started.

Android example

If you are using a platform other than Android, or you are already familiar with the TensorFlow Lite APIs, you can download our trained model.

Download model

How it works

The model is built for a game agent to play a small board game called 'Plane Strike'. For a quick introduction of this game and its rules, please refer to this README.

Underneath the app's UI, we have built an agent that plays against the human player. The agent is a 3-layer MLP that takes the board state as input and outputs the predicted score for each of the 64 possible board cells. The model is trained using policy gradient (REINFORCE) and you can find the training code here. After training the agent, we convert the model into TFLite and deploy it in the Android app.

During the actual game play in the Android app, when it's the agent's turn to take action, the agent looks at the human player's board state (the board at the bottom), which contains information about previous successful and unsuccessful strikes (hits and misses), and uses the trained model to predict where to strike next, so that it can finish the game before the human player does.

Performance benchmarks

Performance benchmark numbers are generated with the tool described here.

Model Name Model size Device CPU
Policy Gradient 84 Kb Pixel 3 (Android 10) 0.01ms*
Pixel 4 (Android 10) 0.01ms*

* 1 threads used.

Inputs

The model accepts a 3-D float32 Tensor of (1, 8, 8) as the board state.

Outputs

The model returns a 2-D float32 Tensor of shape (1,64) as the predicted scores for each of the 64 possible strike positions.

Train your own model

You could train your own model for a larger/smaller board by change the BOARD_SIZE parameter in the training code.