模型:
sb3/td3-Swimmer-v3
这是使用 stable-baselines3 library 和 RL Zoo 训练的 TD3 代理在 Swimmer-v3 上进行游戏的训练模型。
RL Zoo 是一个训练强化学习代理的稳定 Baselines3 框架,包含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 td3 --env Swimmer-v3 -orga sb3 -f logs/ python enjoy.py --algo td3 --env Swimmer-v3 -f logs/
python train.py --algo td3 --env Swimmer-v3 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo td3 --env Swimmer-v3 -f logs/ -orga sb3
OrderedDict([('gamma', 0.9999), ('gradient_steps', 1), ('learning_starts', 10000), ('n_timesteps', 1000000.0), ('noise_std', 0.1), ('noise_type', 'normal'), ('policy', 'MlpPolicy'), ('train_freq', 1), ('normalize', False)])