/random-network-distillation-pytorch

Random Network Distillation pytorch

Primary LanguagePythonMIT LicenseMIT

Random Network Distillation

Intrinsic Reward Graph with play

Venture Montezuma's Revenge
Video Label
~ New model for Montezuma
  • Advantage Actor critic [1]
  • Parallel Advantage Actor critic [2]
  • Exploration by Random Network Distillation [3]
  • Proximal Policy Optimization Algorithms [4]

1. Setup

Requirements


2. How to Train

Modify the parameters in config.conf as you like.

python train.py

3. How to Eval

python eval.py

4. Loss/Reward Graph

  • Montezuma's Revenge Env image
  • Venture Env image

References

[1] Actor-Critic Algorithms
[2] Efficient Parallel Methods for Deep Reinforcement Learning
[3] Exploration by Random Network Distillation
[4] Proximal Policy Optimization Algorithms