Projective Simulation
  • Get started
  • Documentation
  • Tutorials
  • Research

Core

  • Documentation
  • Agents
    • Core
    • Foraging
  • ECMs
    • Core
    • Priming
  • Environments
    • Core
    • Foraging

On this page

  • Abstract Environment
    • Abstract_Env
  • RLGL
    • RLGL
    • Invader Game
      • Invader_Game_Env
    • Grid World Environment
      • Grid_World_Env

View source

Report an issue

Core

Abstract Environment


source

Abstract_Env

 Abstract_Env (state:object)

Abstract environment from which other environments can de derived.

RLGL

A description


source

RLGL

 RLGL (state=0, transition_matrix=None)

Abstract environment from which other environments can de derived.

A minimal example

Invader Game

Add a description


source

Invader_Game_Env

 Invader_Game_Env (state=None, transition_matrix=None)

Abstract environment from which other environments can de derived.

Grid World Environment

Grid world is a navigation task in a 2D environment configurated as a grid, with obstacles. The goal is for the agent to reach a target at a certain position, which entails the agent exploring enough and remembering some of its past actions. Observations consist of the agent’s coordinates and actions of the set of allowed displacements in the grid.


source

Grid_World_Env

 Grid_World_Env (dimensions=(10, 10), N_obstacles=10,
                 obstacle_locations=None, reward_location=None,
                 state=None)

Abstract environment from which other environments can de derived.