DeepRL:一些深度RL算法的实现
需积分: 14 168 浏览量
2021-03-07
15:50:43
上传
评论
收藏 3.19MB ZIP 举报
DeepRL-main.zip （44个子文件） 
DeepRL-main 03.DDPG Pendulum-v0_Model 
critic.pth 480KB actor.pth 478KB events.out.tfevents.1613993037.TaodeMacBook-Pro.local 23KB
Reward_Epi_reward.svg 39KB Agent.py 4KB ReplayBuffer.py 1KB DDPG.py 3KB Net.py 954B LICENSE 1KB 02.AC Train.py 1KB Config.py 608B AC_MountainCar-v0_Model Model_training100Times.pkl 137B Agent.py 2KB Net.py 679B 04.TD3 Pendulum-v0_Model events.out.tfevents.1614945162.TaodeMacBook-Pro.local 643B critic2.pth 480KB events.out.tfevents.1614946860.TaodeMacBook-Pro.local 14KB critic1.pth 480KB events.out.tfevents.1614945095.TaodeMacBook-Pro.local 93B events.out.tfevents.1614222608.TaodeMacBook-Pro.local 20KB events.out.tfevents.1614946846.TaodeMacBook-Pro.local 2KB actor.pth 478KB Reward_Epi_reward.svg 38KB TD3.py 3KB Agent.py 5KB ReplayBuffer.py 1KB Net.py 954B .gitignore 2KB 05.SAC SAC.py 3KB Pendulum-v0_Model events.out.tfevents.1614948746.TaodeMacBook-Pro.local 15KB critic2.pth 264KB value_net.pth 263KB critic1.pth 264KB actor.pth 264KB Agent.py 6KB ReplayBuffer.py 1KB Net.py 2KB Utils.py 524B 01.DQN Train.py 2KB Config.py 616B Agent.py 3KB ReplayBuffer.py 503B Net.py 651B README.md 173B资源评论
