PPO Agent playing seals/CartPole-v0
This is a trained model of a PPO agent playing seals/CartPole-v0 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 ppo --env seals/CartPole-v0 -orga HumanCompatibleAI -f logs/
python -m rl_zoo3.enjoy --algo ppo --env seals/CartPole-v0 -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 ppo --env seals/CartPole-v0 -orga HumanCompatibleAI -f logs/
python -m rl_zoo3.enjoy --algo ppo --env seals/CartPole-v0 -f logs/
Training (with the RL Zoo)
python -m rl_zoo3.train --algo ppo --env seals/CartPole-v0 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo ppo --env seals/CartPole-v0 -f logs/ -orga HumanCompatibleAI
Hyperparameters
OrderedDict([('batch_size', 256),
('clip_range', 0.4),
('ent_coef', 0.008508727919228772),
('gae_lambda', 0.9),
('gamma', 0.9999),
('learning_rate', 0.0012403278189645594),
('max_grad_norm', 0.8),
('n_envs', 8),
('n_epochs', 10),
('n_steps', 512),
('n_timesteps', 100000.0),
('policy', 'MlpPolicy'),
('policy_kwargs',
{'activation_fn': <class 'torch.nn.modules.activation.ReLU'>,
'net_arch': [{'pi': [64, 64], 'vf': [64, 64]}]}),
('vf_coef', 0.489343896591493),
('normalize', False)])
Environment Arguments
{'render_mode': 'rgb_array'}
- Downloads last month
- 2,073
Evaluation results
- mean_reward on seals/CartPole-v0self-reported500.00 +/- 0.00