PPO Agent playing seals/MountainCar-v0

This is a trained model of a PPO agent playing seals/MountainCar-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
# Download model and save it into the logs/ folder<br /> python -m rl_zoo3.load_from_hub --algo ppo --env seals/MountainCar-v0 -orga HumanCompatibleAI -f logs/<br /> python enjoy.py --algo ppo --env seals/MountainCar-v0 -f logs/<br />

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/MountainCar-v0 -orga HumanCompatibleAI -f logs/<br /> rl_zoo3 enjoy --algo ppo --env seals/MountainCar-v0 -f logs/<br />

Training (with the RL Zoo)

python train.py --algo ppo --env seals/MountainCar-v0 -f logs/<br /> # Upload the model and generate video (when possible)<br /> python -m rl_zoo3.push_to_hub --algo ppo --env seals/MountainCar-v0 -f logs/ -orga HumanCompatibleAI<br />

Hyperparameters

OrderedDict([('batch_size', 512),<br /> ('clip_range', 0.2),<br /> ('ent_coef', 6.4940755116195606e-06),<br /> ('gae_lambda', 0.98),<br /> ('gamma', 0.99),<br /> ('learning_rate', 0.0004476103728105138),<br /> ('max_grad_norm', 1),<br /> ('n_envs', 16),<br /> ('n_epochs', 20),<br /> ('n_steps', 256),<br /> ('n_timesteps', 1000000.0),<br /> ('normalize',<br /> {'gamma': 0.99, 'norm_obs': False, 'norm_reward': True}),<br /> ('policy', 'MlpPolicy'),<br /> ('policy_kwargs',<br /> {'activation_fn': <class 'torch.nn.modules.activation.Tanh'>,<br /> 'features_extractor_class': <class 'imitation.policies.base.NormalizeFeaturesExtractor'>,<br /> 'net_arch': [{'pi': [64, 64], 'vf': [64, 64]}]}),<br /> ('vf_coef', 0.25988158989488963),<br /> ('normalize_kwargs',<br /> {'norm_obs': {'gamma': 0.99,<br /> 'norm_obs': False,<br /> 'norm_reward': True},<br /> 'norm_reward': False})])<br />