genrl
genrl copied to clipboard
SforAiDl
A PyTorch reinforcement learning library for generalizable and reproducible algorithm implementations with an aim to improve accessibility in RL
Objects should be the same else an error should be raised.
1. Doubly-Robust Policy Evaluation 2. Etc
genrl 0.0.2 requires gym 0.17.1 whereas pettingzoo 1.3.3 requires gym 0.17.2
This is a very barebones implementation of maddpg. To Do : - [x] Complete PettingZooInterface - [ ] test training - [ ] Other misc things
This is a _very_ rough draft of a trainer for distributed off policy agents. Currently working on getting DDPG to be trained in distributed manner using this.
PyTorch Lightning automates away most of the engineering required on PyTorch for features like multi-GPU distributed training, early stopping, etc. More details can be found on the blog for the...
Current Logging only allows printing dictionaries, a free form should be allowed too. Some thinking needs to be done as to how to make this happen without breaking the regular...
