eprllib.Agents.Rewards.RewardSpec

eprllib.Agents.Rewards.RewardSpec#

Specification for agent reward functions#

This module defines the RewardSpec class, which is used to specify the configuration of reward functions for agents in reinforcement learning environments.

It ensures that the reward function is properly defined and adheres to the expected interface.

Classes

RewardSpec([reward_fn, reward_fn_config])

RewardSpec is the base class for an reward specification to safe configuration of the object.