Skip to content

Left or right control problem environment for OpenAI gym.

Notifications You must be signed in to change notification settings

gpldecha/gym-leftright

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

gym-leftright

Build Status

Left or right control problem environment. An agent must either reach the left or right boundary of a 1D world. See Tree-Based Batch Mode Reinforcement Learning for a description of the problem.

Installation

pip install gym-leftright

Quick example

  
  import gym
  import gym_leftright
  
  env = gym.make('leftright-v0')
  env.reset()
  
  for _ in range(50):
    env.render()
    action = env.action_space.sample()
    observation, reward, done, info = env.step(action)

About

Left or right control problem environment for OpenAI gym.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages