Skip to content
/ tf_A3C_BipedalWalker Public

BipedalWalker environment from gym, solved with Asynchronous Advantage Actor Critic algorithm using Tensorflow.

2 stars 2 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

galinator9000/tf_A3C_BipedalWalker

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits

.vscode

.vscode

 
 

__pycache__

__pycache__

 
 

model

model

 
 

.gitignore

.gitignore

 
 

A3CAgentContinuous.py

A3CAgentContinuous.py

 
 

README.md

README.md

 
 

Worker.py

Worker.py

 
 

test.py

test.py

 
 

train.py

train.py

 
 

Repository files navigation

tf_A3C_BipedalWalker

BipedalWalker environment from gym, solved with Asynchronous Advantage Actor Critic algorithm using Tensorflow.

Agent trained about 30000 episodes per worker in ~21 hour on a single CPU, with 4 workers.

BipedalWalker-v2 with A3C Algorithm

About

BipedalWalker environment from gym, solved with Asynchronous Advantage Actor Critic algorithm using Tensorflow.

Topics

learning algorithm tensorflow policy actor openai gym policy-gradient gradient a3c reinforcement walker bipedal actor-critic critic a2c

Resources

Readme
Activity

Stars

2 stars

Watchers

0 watching

Forks

2 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages