模型:
sb3/ppo_lstm-MountainCarContinuousNoVel-v0
这是一个经过训练的 RecurrentPPO 代理在 MountainCarContinuousNoVel-v0 游戏中的表现,使用了 stable-baselines3 library 和 RL Zoo 的模型。
RL Zoo 是一个训练框架,用于稳定的 Baselines3 强化学习代理的训练,包括了超参数优化和预训练代理。
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 ppo_lstm --env MountainCarContinuousNoVel-v0 -orga sb3 -f logs/ python enjoy.py --algo ppo_lstm --env MountainCarContinuousNoVel-v0 -f logs/
python train.py --algo ppo_lstm --env MountainCarContinuousNoVel-v0 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo ppo_lstm --env MountainCarContinuousNoVel-v0 -f logs/ -orga sb3
OrderedDict([('batch_size', 256), ('clip_range', 0.1), ('ent_coef', 0.00429), ('gae_lambda', 0.9), ('gamma', 0.9999), ('learning_rate', 7.77e-05), ('max_grad_norm', 5), ('n_envs', 8), ('n_epochs', 10), ('n_steps', 1024), ('n_timesteps', 300000.0), ('normalize', True), ('policy', 'MlpLstmPolicy'), ('policy_kwargs', 'dict(log_std_init=0.0, ortho_init=False, lstm_hidden_size=32, ' 'enable_critic_lstm=True, net_arch=[dict(pi=[64], vf=[64])])'), ('sde_sample_freq', 8), ('use_sde', True), ('vf_coef', 0.19), ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])