metadata
tags:
- Hopper-v4
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
library_name: cleanrl
model-index:
- name: SAC
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Hopper-v4
type: Hopper-v4
metrics:
- type: mean_reward
value: 1680.67 +/- 734.03
name: mean_reward
verified: false
(CleanRL) SAC Agent Playing Hopper-v4
This is a trained model of a SAC agent playing Hopper-v4. The model was trained by using CleanRL and the most up-to-date training code can be found here.
Get Started
To use this model, please install the cleanrl
package with the following command:
pip install "cleanrl[sac_continuous_action]"
python -m cleanrl_utils.enjoy --exp-name sac_continuous_action --env-id Hopper-v4
Please refer to the documentation for more detail.
Command to reproduce the training
curl -OL https://huggingface.co/sdpkjc/Hopper-v4-sac_continuous_action-seed5/raw/main/sac_continuous_action.py
curl -OL https://huggingface.co/sdpkjc/Hopper-v4-sac_continuous_action-seed5/raw/main/pyproject.toml
curl -OL https://huggingface.co/sdpkjc/Hopper-v4-sac_continuous_action-seed5/raw/main/poetry.lock
poetry install --all-extras
python sac_continuous_action.py --save-model --upload-model --hf-entity sdpkjc --env-id Hopper-v4 --seed 5 --track
Hyperparameters
{'alpha': 0.2,
'autotune': True,
'batch_size': 256,
'buffer_size': 1000000,
'capture_video': False,
'cuda': True,
'env_id': 'Hopper-v4',
'exp_name': 'sac_continuous_action',
'gamma': 0.99,
'hf_entity': 'sdpkjc',
'learning_starts': 5000.0,
'noise_clip': 0.5,
'policy_frequency': 2,
'policy_lr': 0.0003,
'q_lr': 0.001,
'save_model': True,
'seed': 5,
'target_network_frequency': 1,
'tau': 0.005,
'torch_deterministic': True,
'total_timesteps': 1000000,
'track': True,
'upload_model': True,
'wandb_entity': None,
'wandb_project_name': 'cleanRL'}