Skip to content

Latest commit

 

History

History
42 lines (29 loc) · 1.37 KB

README.md

File metadata and controls

42 lines (29 loc) · 1.37 KB

Reinforcement-Implementation

This project aims to reproduce the results of several model-free RL algorithms in continuous action domain (mujuco environment).

This projects

  • uses pytorch package
  • implements different algorithms independently in seperate files
  • is written in simplest style
  • tries to follow the original paper and reproduce their results

My first stage of work is to reproduce this figure in the PPO paper.

  • A2C
  • ACER (A2C + Trust Region): It seems that this implementation has some problems ... (welcome bug report)
  • CEM
  • TRPO (TRPO single path)
  • PPO (PPO clip)
  • Vanilla PG

On the next stage, I want to implement

Then next stage, discrete action space problem and raw video input (Atari) problems ...

  • DQN and relevant techniques (target network / double Q-learning / prioritized experience replay / dueling network structure)

And then model-based algorithms

  • PILCO
  • PE-TS

TODOs:

  • change the way reward counts, current way may underestimate the reward

PPO Implementation

PPO implementation is of high quality - matches the performance of openai.baselines.