jvmncs / ParamNoise

A comparison of parameter space noise methods for exploration in deep reinforcement learning

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ParamNoise

A comparison of parameter space noise methods for exploration in deep reinforcement learning

NOTE: This project is not maintained. Reach out if you'd like to help reboot it.

Links to papers

Parameter Space Noise for Exploration : https://openreview.net/forum?id=ByBAl2eAZ&noteId=ByBAl2eAZ

Noisy Networks For Exploration : https://openreview.net/forum?id=rywHCPkAW&noteId=rywHCPkAW

Resources

TODOs

  • Implement PPO and MuJoCo env handling
  • Revisit logging; make sure everything is there to reproduce results in papers
  • Implement plotting (matplotlib is in Logger object; maybe try out visdom)
  • More tests (figure out different combinations of arguments to ensure everything's interacting well)
  • Begin experiments (start with Mujoco; it's cheaper)

Atari Games to Test

  • Alien: Adaptive helps a lot, learned shows no improvement
  • Enduro: Both methods improve
  • Seaquest: Adaptive helps, learned performs worse than baseline
  • Space Invaders: Adaptive helps, but learned helps more
  • WizardOfWor: Adaptive worse than baseline, but learned helps a lot

MuJoCo enviroments to test

  • Hopper
  • Walker2d
  • HalfCheetah
  • Sparse versions of these? (from rllab)

About

A comparison of parameter space noise methods for exploration in deep reinforcement learning

License:MIT License


Languages

Language:Python 100.0%