Module relearn::envs [−][src]
Expand description
Reinforcement learning environments
Structs
A multi-armed bandit
Chain Environment
Random distribution over MDPs with Dirichlet sampled transition probabilities.
Wrapper that provides the inner environment structure of a meta environment.
Memory Game Environment
A meta reinforcement learning environment with internal state.
Configuration for MetaEnv
A meta reinforcement learning environment that treats RL itself as an environment.
Distribution over deterministic bandits in which one arm has reward 1 and the rest have 0.
Wraps a Pomdp as a Environment.
Environment wrapper that cuts off episodes after a set number of steps.
Stored copy of an environment structure.
A distribution over Beroulli bandit environments with uniformly sampled means.
A basic wrapped object.
Enums
Error building an environment
Traits
Build an Environment.
Build an EnvDistribution.
Build a Pomdp.
Build a PomdpDistribution.
Marker indiciating that this object can build itself by cloning.
A distribution of environments sharing the same external structure.
The external structure of a reinforcement learning environment.
A reinforcement learning environment with internal state.
Convert into an Environment.
A Markov decision process (MDP).
A partially observable Markov decision process (POMDP).
A distribution of Pomdp sharing the same external structure.
An Environment with consistent EnvStructure.
Type Definitions
A multi-armed bandit where each arm samples from a Bernoulli distribution.
A multi-armed bandit where each arm has a determistic distribution.
Meta-environment observation space. See MetaPomdp for details.
Wrap an environment with a per-episode step limit.