metadata
library_name: stable-baselines3
tags:
- Hopper-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: ARS
results:
- metrics:
- type: mean_reward
value: 3343.48 +/- 8.53
name: mean_reward
task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Hopper-v3
type: Hopper-v3
ARS Agent playing Hopper-v3
This is a trained model of a ARS agent playing Hopper-v3 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
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo ars --env Hopper-v3 -orga sb3 -f logs/
python enjoy.py --algo ars --env Hopper-v3 -f logs/
Training (with the RL Zoo)
python train.py --algo ars --env Hopper-v3 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo ars --env Hopper-v3 -f logs/ -orga sb3
Hyperparameters
OrderedDict([('alive_bonus_offset', -1),
('delta_std', 0.025),
('learning_rate', 0.01),
('n_delta', 8),
('n_envs', 16),
('n_timesteps', 7000000.0),
('n_top', 4),
('normalize', 'dict(norm_obs=True, norm_reward=False)'),
('policy', 'LinearPolicy'),
('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])