Huggingface Hub Integration

List and videos of trained agents can be found on our Huggingface page:

Upload model to hub (same syntax as for

python -m rl_zoo3.push_to_hub --algo ppo --env CartPole-v1 -f logs/ -orga sb3 -m "Initial commit"

you can choose custom repo-name (default: {algo}-{env_id}) by passing a --repo-name argument.

Download model from hub:

python -m rl_zoo3.load_from_hub --algo ppo --env CartPole-v1 -f logs/ -orga sb3

Experiment tracking

We support tracking experiment data such as learning curves and hyperparameters via Weights and Biases.

The following command

python --algo ppo --env CartPole-v1 --track --wandb-project-name sb3

yields a tracked experiment at this URL.

To add a tag to the run, (e.g. optimized), use the argument --wandb-tags optimized.