vwxyzjn / cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
http://docs.cleanrl.dev
Other
4.84k stars 560 forks source link

KeyError: 'cleanba_ppo_envpool_procgen' #452

Open zhixiongzh opened 3 months ago

zhixiongzh commented 3 months ago

Problem Description

Checklist

Current Behavior

can not load the model from HF, get the error when I run python -m cleanrl_utils.enjoy --exp-name cleanba_ppo_envpool_procgen --env-id CoinrunHard-v0

KeyError: 'cleanba_ppo_envpool_procgen'

Expected Behavior

I should be able to see the performance of pretrained policy in HF

Possible Solution

Is this exp deprecated?

Steps to Reproduce

curl -sSL https://install.python-poetry.org | python3 -
git clone https://github.com/vwxyzjn/cleanrl.git && cd cleanrl
poetry install
pip3 install -r requirements/requirements.txt
pip3 install -r requirements/requirements-procgen.txt
poetry install -E procgen
pip install "cleanrl[jax,envpool,atari]"
python -m cleanrl_utils.enjoy --exp-name cleanba_ppo_envpool_procgen --env-id CoinrunHard-v0