search

twni2016 / pomdp-baselines

Simple (but often Strong) Baselines for POMDPs in PyTorch, ICML 2022
https://sites.google.com/view/pomdp-baselines
MIT License
293 stars 41 forks source link

Plan for recurrent soft Q-learning and DRQN? #10

Closed hai-h-nguyen closed 2 years ago

hai-h-nguyen commented 2 years ago

As the title says.

twni2016 commented 2 years ago

Hi,

I currently do not have plan on DQN-style implementation, as I focus on actor-critic methods, and need to refactor the code for actor-critic into Q-learning. There have been some github repos on DRQN https://github.com/keep9oing/DRQN-Pytorch-CartPole-v1

Feel free to pull request if you think it worth adding DQN-style methods into this repo.