README.md
| 1 | --- |
| 2 | library_name: stable-baselines3 |
| 3 | tags: |
| 4 | - BipedalWalkerHardcore-v3 |
| 5 | - deep-reinforcement-learning |
| 6 | - reinforcement-learning |
| 7 | - stable-baselines3 |
| 8 | model-index: |
| 9 | - name: SAC |
| 10 | results: |
| 11 | - metrics: |
| 12 | - type: mean_reward |
| 13 | value: 11.30 +/- 107.41 |
| 14 | name: mean_reward |
| 15 | task: |
| 16 | type: reinforcement-learning |
| 17 | name: reinforcement-learning |
| 18 | dataset: |
| 19 | name: BipedalWalkerHardcore-v3 |
| 20 | type: BipedalWalkerHardcore-v3 |
| 21 | --- |
| 22 | |
| 23 | # **SAC** Agent playing **BipedalWalkerHardcore-v3** |
| 24 | This is a trained model of a **SAC** agent playing **BipedalWalkerHardcore-v3** |
| 25 | using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) |
| 26 | and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). |
| 27 | |
| 28 | The RL Zoo is a training framework for Stable Baselines3 |
| 29 | reinforcement learning agents, |
| 30 | with hyperparameter optimization and pre-trained agents included. |
| 31 | |
| 32 | ## Usage (with SB3 RL Zoo) |
| 33 | |
| 34 | RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> |
| 35 | SB3: https://github.com/DLR-RM/stable-baselines3<br/> |
| 36 | SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib |
| 37 | |
| 38 | ``` |
| 39 | # Download model and save it into the logs/ folder |
| 40 | python -m rl_zoo3.load_from_hub --algo sac --env BipedalWalkerHardcore-v3 -orga sb3 -f logs/ |
| 41 | python enjoy.py --algo sac --env BipedalWalkerHardcore-v3 -f logs/ |
| 42 | ``` |
| 43 | |
| 44 | ## Training (with the RL Zoo) |
| 45 | ``` |
| 46 | python train.py --algo sac --env BipedalWalkerHardcore-v3 -f logs/ |
| 47 | # Upload the model and generate video (when possible) |
| 48 | python -m rl_zoo3.push_to_hub --algo sac --env BipedalWalkerHardcore-v3 -f logs/ -orga sb3 |
| 49 | ``` |
| 50 | |
| 51 | ## Hyperparameters |
| 52 | ```python |
| 53 | OrderedDict([('batch_size', 256), |
| 54 | ('buffer_size', 1000000), |
| 55 | ('ent_coef', 0.005), |
| 56 | ('gamma', 0.99), |
| 57 | ('gradient_steps', 1), |
| 58 | ('learning_rate', 'lin_7.3e-4'), |
| 59 | ('learning_starts', 10000), |
| 60 | ('n_timesteps', 10000000.0), |
| 61 | ('policy', 'MlpPolicy'), |
| 62 | ('policy_kwargs', 'dict(net_arch=[400, 300])'), |
| 63 | ('tau', 0.01), |
| 64 | ('train_freq', 1), |
| 65 | ('normalize', False)]) |
| 66 | ``` |
| 67 | |