https://github.com/embersarc/ppo

PPO implementation for OpenAI gym environment based on Unity ML Agents
https://github.com/embersarc/ppo

Last synced: 2 months ago
JSON representation

PPO implementation for OpenAI gym environment based on Unity ML Agents

• Host: GitHub
• URL: https://github.com/embersarc/ppo
• Owner: EmbersArc
• Created: 2017-12-29T15:57:46.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2018-03-17T13:55:53.000Z (about 7 years ago)
• Last Synced: 2025-02-27T05:56:15.713Z (3 months ago)
• Language: Python
• Size: 7.9 MB
• Stars: 149
• Watchers: 10
• Forks: 21
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# PPO

PPO implementation for OpenAI gym environment based on Unity ML Agents: https://github.com/Unity-Technologies/ml-agents

Notable changes include:

  * Ability to continuously display progress with non-stochastic policy during training

  * Works with OpenAI environments

  * Option to record episodes

  * State normalization for given number of frames

  * Frame skip

  * Faster reward discounting etc.