C#/.net>> random-network-distillation-pytorch>> 返回
项目作者： jcwleo

项目描述 ：
Random Network Distillation pytorch
高级语言： Python
项目地址: git://github.com/jcwleo/random-network-distillation-pytorch.git
创建时间： 2018-11-12T02:30:43Z
项目社区：https://github.com/jcwleo/random-network-distillation-pytorch
开源协议：MIT License
下载


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.

  1. python train.py

3. How to Eval

  1. 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