OpenAI Gym

class tensorforce.environments.OpenAIGym(level, visualize=False, max_episode_timesteps=None, terminal_reward=0.0, reward_threshold=None, tags=None, monitor_directory=None, **kwargs)[source]

OpenAI Gym environment adapter (specification key: gym, openai_gym).

May require:

pip install gym[all]
Parameters:
  • level (string) – Gym id (required).
  • visualize (bool) – Whether to visualize interaction (default: false).
  • max_episode_timesteps (false | int > 0) – Whether to terminate an episode after a while, and if so, maximum number of timesteps per episode (default: Gym default).
  • terminal_reward (float) – Additional reward for early termination, if otherwise indistinguishable from termination due to maximum number of timesteps (default: Gym default).
  • reward_threshold (float) – Gym environment argument, the reward threshold before the task is considered solved (default: Gym default).
  • tags (dict) – Gym environment argument, a set of arbitrary key-value tags on this environment, including simple property=True tags (default: Gym default).
  • monitor_directory (string) – Monitor output directory (default: none).
  • kwargs – Additional Gym environment arguments.