search

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

Reproduction util: wrong command path #440

Open qgallouedec opened 6 months ago

qgallouedec commented 6 months ago

Small issue:

$ python -m cleanrl_utils.reproduce --run openrlbenchmark/cleanrl/runs/c1y1qnz4

# run the following
python3 -m venv venv
source venv/bin/activate
pip install -r https://api.wandb.ai/files/openrlbenchmark/cleanrl/c1y1qnz4/requirements.txt
curl -OL https://api.wandb.ai/files/openrlbenchmark/cleanrl/c1y1qnz4/code/cleanrl/ppo_atari.py
python /fsx/costa/cleanrl/cleanrl/ppo_atari.py --track --env-id BreakoutNoFrameskip-v4 --seed 3

it should be

- python /fsx/costa/cleanrl/cleanrl/ppo_atari.py --track --env-id BreakoutNoFrameskip-v4 --seed 3
+ python ppo_atari.py --track --env-id BreakoutNoFrameskip-v4 --seed 3