Python-深度增强学习算法的PyTorch实现策略梯度生成对抗模仿学习

[{"title":"（ 23 个子文件 5.41MB ） Python-深度增强学习算法的PyTorch实现策略梯度生成对抗模仿学习","children":[{"title":"PyTorch-RL-master","children":[{"title":"core","children":[{"title":"trpo.py <span style='color:#111;'> 4.56KB </span>","children":null,"spread":false},{"title":"agent.py <span style='color:#111;'> 5.30KB </span>","children":null,"spread":false},{"title":"ppo.py <span style='color:#111;'> 1.01KB </span>","children":null,"spread":false},{"title":"a2c.py <span style='color:#111;'> 729B </span>","children":null,"spread":false},{"title":"common.py <span style='color:#111;'> 841B </span>","children":null,"spread":false}],"spread":true},{"title":"assets","children":[{"title":"expert_traj","children":[{"title":"Hopper-v2_expert_traj.p <span style='color:#111;'> 5.34MB </span>","children":null,"spread":false}],"spread":true},{"title":"learned_models","children":[{"title":"Hopper-v2_ppo.p <span style='color:#111;'> 291.89KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"models","children":[{"title":"mlp_critic.py <span style='color:#111;'> 902B </span>","children":null,"spread":false},{"title":"mlp_discriminator.py <span style='color:#111;'> 905B </span>","children":null,"spread":false},{"title":"mlp_policy_disc.py <span style='color:#111;'> 1.66KB </span>","children":null,"spread":false},{"title":"mlp_policy.py <span style='color:#111;'> 2.37KB </span>","children":null,"spread":false}],"spread":true},{"title":"utils","children":[{"title":"zfilter.py <span style='color:#111;'> 1.50KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 139B </span>","children":null,"spread":false},{"title":"torch.py <span style='color:#111;'> 1.90KB </span>","children":null,"spread":false},{"title":"replay_memory.py <span style='color:#111;'> 862B </span>","children":null,"spread":false},{"title":"math.py <span style='color:#111;'> 371B </span>","children":null,"spread":false},{"title":"tools.py <span style='color:#111;'> 126B </span>","children":null,"spread":false}],"spread":true},{"title":"examples","children":[{"title":"trpo_gym.py <span style='color:#111;'> 5.28KB </span>","children":null,"spread":false},{"title":"ppo_gym.py <span style='color:#111;'> 6.44KB </span>","children":null,"spread":false},{"title":"a2c_gym.py <span style='color:#111;'> 5.17KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 2.24KB </span>","children":null,"spread":false},{"title":"gail","children":[{"title":"gail_gym.py <span style='color:#111;'> 7.52KB </span>","children":null,"spread":false},{"title":"save_expert_traj.py <span style='color:#111;'> 2.47KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}]