AgentPOV#
- class curiosity_gym.core.agentpov.AgentPOV(action_space: Discrete, observation_space: Box, env_size: tuple[int, int])#
Abstract agent point-of-view class.
Implements the processing of inputs going into a grid environment (actions) and outputs coming out of a grid environment (observations). The
transform_obs()method has to be implemented by inheriting pov classes.- Parameters:
action_space (gymnasium.spaces.Discrete) – The action space defining what actions can be taken by an RL agent within a grid environment.
observation_space (gymnasium.spaces.MultiDiscrete) – The observation space defining the structure of the observations being returned by a grid environment.
env_size (tuple[int, int]) – Number of (horizontal, vertical) cells in the grid environment where the pov class is used.
Methods
Check if grid cell at given position is visible by the agent.
Transform given action so that it is compatible with the grid environment.
Transform environment state to agent observation.