1999Diego/Deep-Reinforcement-Learning-under-Partial-Observability

A paper list of Deep Reinforcement Learning algorithms under Partial Obsrvability

Deep-Reinforcement-Learning-under-Partial-Observability

This is a collection of research papers for Deep Reinforcement Learning algorithms under Partial Obsrvability.

Welcome to follow and star!

Table of Contents

• DRL under Partial Observability
  • Table of Contents
  • Overview of POMDP in RL
  • Papers
  • License

Overview of PODMP in RL

Papers

papers

2022

• Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs

  • Tianwei Ni, Benjamin Eysenbach, Ruslan Salakhutdinov
  • Key：
  • Code： Original Code Base
  • ExpEnv:
  • ICML 22

• Deep Transformer Q-Networks for Partially Observable Reinforcement Learning

  • Kevin Esslinger, Robert Platt, Christopher Amato
  • Key: Transformer, DQN
  • Code: Original Code Base
  • ExpEnv:

2015

• Deep Recurrent Q-Learning for Partially Observable MDPs
  • Matthew Hausknecht and Peter Stone
  • Key: RNN, DQN
  • Code:
  • ExpEnv: Atari

benchmarks

License

Deep-Reinforcement-Learning-under-Partial-Observability is released under the Apache 2.0 license.