SAC Agent playing seals/Swimmer-v1
This is a trained model of a SAC agent playing seals/Swimmer-v1 using the stable-baselines3 library and the RL Zoo.
The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo
SB3: https://github.com/DLR-RM/stable-baselines3
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
pip install rl_zoo3
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo sac --env seals/Swimmer-v1 -orga ernestum -f logs/
python -m rl_zoo3.enjoy --algo sac --env seals/Swimmer-v1 -f logs/
If you installed the RL Zoo3 via pip (pip install rl_zoo3
), from anywhere you can do:
python -m rl_zoo3.load_from_hub --algo sac --env seals/Swimmer-v1 -orga ernestum -f logs/
python -m rl_zoo3.enjoy --algo sac --env seals/Swimmer-v1 -f logs/
Training (with the RL Zoo)
python -m rl_zoo3.train --algo sac --env seals/Swimmer-v1 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo sac --env seals/Swimmer-v1 -f logs/ -orga ernestum
Hyperparameters
OrderedDict([('batch_size', 128),
('buffer_size', 100000),
('gamma', 0.995),
('learning_rate', 0.00039981805535514633),
('learning_starts', 1000),
('n_timesteps', 1000000.0),
('policy', 'MlpPolicy'),
('policy_kwargs',
{'log_std_init': -2.689958330139309,
'net_arch': [400, 300],
'use_sde': False}),
('tau', 0.01),
('train_freq', 256),
('normalize', False)])
Environment Arguments
{'render_mode': 'rgb_array'}
- Downloads last month
- 0
Evaluation results
- mean_reward on seals/Swimmer-v1self-reported28.90 +/- 1.67