PPO icon indicating copy to clipboard operation
PPO copied to clipboard

PPO implementation for OpenAI gym environment based on Unity ML Agents

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.