著名的强化学习算法 Proximal Policy Optimization 的另一种自定义实现，也称为 PPO

[{"title":"（ 21 个子文件 25KB ） 著名的强化学习算法 Proximal Policy Optimization 的另一种自定义实现，也称为 PPO","children":[{"title":"ppo-main","children":[{"title":"stochastics.py <span style='color:#111;'> 5.96KB </span>","children":null,"spread":false},{"title":"dojo.py <span style='color:#111;'> 7.23KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 3.95KB </span>","children":null,"spread":false},{"title":"ppo.py <span style='color:#111;'> 17.64KB </span>","children":null,"spread":false},{"title":"test.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"config.toml <span style='color:#111;'> 1.22KB </span>","children":null,"spread":false},{"title":"networks.py <span style='color:#111;'> 1.10KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.06KB </span>","children":null,"spread":false},{"title":"default_config.toml <span style='color:#111;'> 919B </span>","children":null,"spread":false},{"title":"sampler.py <span style='color:#111;'> 3.97KB </span>","children":null,"spread":false},{"title":"scheduler.py <span style='color:#111;'> 1.07KB </span>","children":null,"spread":false},{"title":"buffer.py <span style='color:#111;'> 8.49KB </span>","children":null,"spread":false},{"title":"approximator.py <span style='color:#111;'> 331B </span>","children":null,"spread":false},{"title":"model.py <span style='color:#111;'> 5.51KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.82KB </span>","children":null,"spread":false},{"title":"algorithm.py <span style='color:#111;'> 1.91KB </span>","children":null,"spread":false},{"title":"airl.py <span style='color:#111;'> 3.70KB </span>","children":null,"spread":false},{"title":"modules.py <span style='color:#111;'> 2.23KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 161B </span>","children":null,"spread":false},{"title":"network.py <span style='color:#111;'> 9.94KB </span>","children":null,"spread":false},{"title":"normalizer.py <span style='color:#111;'> 2.76KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]