# Renforcement-robot
基于强化学习（DDPG）的机器人导航算法实现。未收敛代码
基于强化学习（DDPG）的机器人导航算法实现python源码+数据集.zip （58个子文件） 
code_20105 DDPG 
robot_write_csv.py 7KB RL_Robot ou_noise.pyc 2KB replay_buffer.pyc 3KB gym_ddpg.py 2KB critic_network.py 6KB actor_network_bn.pyc 9KB train_data.csv 808KB actor_network.py 8KB data train_4.csv 849KB test_4.csv 87KB train_data.csv 5.03MB train_3.csv 6.61MB state.csv 30KB test_2.csv 1.2MB test_data.csv 112KB test_1.csv 81KB train_2.csv 2.95MB test_3.csv 196KB train_1.csv 764KB critic_network.pyc 6KB test_data.csv 65KB jdcar_supervised.py 1KB replay_buffer.py 2KB object.pyc 12KB actor_network_bn.py 13KB .idea workspace.xml 40KB misc.xml 185B inspectionProfiles Project_Default.xml 421B modules.xml 268B RL_Robot.iml 616B jdcar_ddpg.py 1KB ddpg.pyc 4KB actor_network.pyc 8KB test_actor.py 4KB logs events.out.tfevents.1524042836.ld-TM1604 371KB events.out.tfevents.1524042773.ld-TM1604 371KB events.out.tfevents.1524039070.ld-TM1604 371KB events.out.tfevents.1524038769.ld-TM1604 371KB events.out.tfevents.1524039498.ld-TM1604 371KB events.out.tfevents.1524039033.ld-TM1604 368KB events.out.tfevents.1524038999.ld-TM1604 371KB events.out.tfevents.1524042809.ld-TM1604 371KB events.out.tfevents.1524042851.ld-TM1604 371KB events.out.tfevents.1524039517.ld-TM1604 371KB events.out.tfevents.1524039309.ld-TM1604 371KB events.out.tfevents.1524042587.ld-TM1604 371KB events.out.tfevents.1524042692.ld-TM1604 371KB events.out.tfevents.1524039654.ld-TM1604 371KB events.out.tfevents.1524043264.ld-TM1604 371KB events.out.tfevents.1524042973.ld-TM1604 371KB events.out.tfevents.1524039570.ld-TM1604 371KB ou_noise.py 823B env.py 10KB env.pyc 8KB critic_network_bn.py 7KB ddpg.py 5KB object.py 8KB README.md 98B资源评论
