8000 GitHub - joeljosephjin/gym_2d: Simple 2D Navigation task environment for meta reinforcement learning research.
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

joeljosephjin/gym_2d

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

gym_2d

Simple 2D Navigation task environment for meta reinforcement learning research. Implemented from the paper: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

Test

Use this code to test the environment.

import gym_2d

env = gym_2d.gym_2d()
observation = env.reset()
print('START:- goal:', env.goal)

for i in range(1000):
    env.render()
    action = env.sample_action()
    observation, reward, done = env.step(action)

    if done:
        print('DONE:- reached:', observation,',within dist:', env.dist, ',in steps:', i)
        break
        observation = env.reset()
        
print('END:- reached:', observation,',within dist:', env.dist, ',in steps:', i)

Render Output

Render Output

About

Simple 2D Navigation task environment for meta reinforcement learning research.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

0