PantheonRL
PantheonRL copied to clipboard
Stanford-ILIAD
PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.
The PantheonRL environment wrapper for overcookedgym uses an old version of HumanCompatibleAI's overcooked_ai repo under the hood. Unfortunately, this old version contains a typo in the p1 feature array here:...
Hello! The class MediumLevelPlanner used in overcooked.py seems to be deprecated in the latest overcooked_ai version, which class can be used instead?
I am quite impressed with the work you've accomplished in this area and would be grateful for your insights on a specific technical aspect. Could you please guide me on...
Hi, I adapted the simple example to use ```python import gym from overcookedgym.overcooked_utils import LAYOUT_LIST from pantheonrl.common.agents import OnPolicyAgent, OffPolicyAgent from stable_baselines3 import PPO, DQN layout = "simple" assert layout...
Hi, Could you please offer an example of tester.py? The code worked without a problem with the trainer.py, but the problem occurred with the tester. The error is as follows....
Hi, Could you please offer an example of [bctrainer.py](https://github.com/Stanford-ILIAD/PantheonRL/blob/master/bctrainer.py). I input the trajs file collected from web user interface but meet an error: Traceback (most recent call last): File "/Users/alexwang/phD/PantheonRL/bctrainer.py",...
I'm trying to see if I can use this library to train in petting zoo's waterworld_v4. Running the algorithm this is the error I'm getting, ``` extern "Python": function pymunk._chipmunk.ext_cpBodyShapeIteratorFunc()...
Metadata
Owner
Metadata
PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.