Projective Simulation
  • Get started
  • Documentation
  • Tutorials
  • Research
  1. Environments
  2. Core
  • Documentation
  • Agents
    • Core
    • Foraging
  • ECMs
    • Core
    • Priming
    • State Estimators
  • Environments
    • Core
    • Foraging
    • POMDPs
    • Factorized POMDPs

On this page

  • Abstract Environment
  • Invader Game
  • Grid World Environment
  • View source
  • Report an issue
  1. Environments
  2. Core

Core

Abstract Environment


source

Abstract_Env

def Abstract_Env(
    state:object
):

Abstract environment from which other environments can de derived.

Invader Game


source

Invader_Game_Env

def Invader_Game_Env(
    state:NoneType=None, transition_matrix:NoneType=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

def Grid_World_Env(
    dimensions:tuple=(10, 10), N_obstacles:int=10, obstacle_locations:NoneType=None, reward_location:NoneType=None,
    state:NoneType=None
):

Abstract environment from which other environments can de derived.

  • View source
  • Report an issue