Skip to content

environments.md

Latest commit

 

History

History
59 lines (46 loc) · 1.3 KB

environments.md

File metadata and controls

59 lines (46 loc) · 1.3 KB

Environments

A reinforcement learning environment provides the API to a simulated or real environment as the subject for optimization. It could be anything from video games (e.g. Atari) to robots or trading systems. The agent interacts with this environment and learns to act optimally in its dynamics.

Environment <-> Runner <-> Agent <-> Model

    .. autoclass:: tensorforce.environments.Environment
        :members:
        :noindex:

Ready-to-use environments

OpenAI Gym

    .. autoclass:: tensorforce.contrib.openai_gym.OpenAIGym
        :noindex:
        :show-inheritance:
        :members:
        :special-members: __init__

OpenAI Universe

    .. autoclass:: tensorforce.contrib.openai_universe.OpenAIUniverse
        :noindex:
        :show-inheritance:
        :members:
        :special-members: __init__

Deepmind Lab

    .. autoclass:: tensorforce.contrib.deepmind_lab.DeepMindLab
        :noindex:
        :show-inheritance:
        :members:
        :special-members: __init__

Unreal Engine 4 Games

    .. autoclass:: tensorforce.contrib.unreal_engine.UE4Environment
        :noindex:
        :show-inheritance:
        :members:
        :special-members: __init__