Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

Module: tf_agents.environments.tf_environment

View source on GitHub

TensorFlow RL Environment API.

Represents a task to be solved, an environment has to define three methods: reset, current_time_step and step.

  • The reset() method returns current time_step after resetting the environment.
  • The current_time_step() method returns current time_step initializing the environmet if needed. Only needed in graph mode.
  • The step(action) method applies the action and returns the new time_step.

Classes

class TFEnvironment: Abstract base class for TF RL environments.