Skip to content

A distributed reinforcement learning framework

Notifications You must be signed in to change notification settings

AltmanD/rl-framework

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RL Framework

A distributed reinforcement learning framework

Getting Started

export HOROVOD_GPU_OPERATIONS=NCCL

Environment Install (conda or docker)

  1. conda env (do not available in windows)
conda env create -f learner/build/conda/env_linux.yaml
  1. docker env
cd learner/build/docker/
docker build -t $name:$tag .

Change config in learner/examples/xxx/xxxx.yaml and actor/examples/xxx/xxxx.yaml

Modify the startup script, and start it

bash start.bash

If want kill all process

bash kill.bash

Default parameters saved in learner/examples/xxx/xxxx.yaml and actor/examples/xxx/xxxx.yaml

About

A distributed reinforcement learning framework

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 97.4%
  • Dockerfile 2.5%
  • Shell 0.1%