Module border_core::core::base[][src]

Expand description

Core functionalities.

Structs

Represents all information given at every step of agent-envieronment interaction. reward and is_done have the same length, the number of processes (environments).

Traits

Represents an action of the environment.

Represents a trainable policy on an environment.

Represents an environment, typically an MDP.

Represents additional information to Obs and Act.

Represents an observation of the environment.

Represents a policy. on an environment. It is based on a mapping from an observation to an action. The mapping can be either of deterministic or stochastic.