songrotek:CSDN认证博客专家
博客地址：https://blog.csdn.net/songrotek
songrotek:CSDN认证博客专家
博客地址：https://blog.csdn.net/songrotek
Paper Reading 4:Massively Parallel Methods for Deep Reinforcement Learning
DRL前沿之：Benchmarking Deep Reinforcement Learning for Continuous Control
DRL前沿之：Hierarchical Deep Reinforcement Learning
解密Google Deepmind AlphaGo围棋算法：真人工智能来自于哪里？
DRL前沿之：Benchmarking Deep Reinforcement Learning for Continuous Control
增强学习Reinforcement Learning经典算法梳理1：policy and value iteration
从头开始安装Ubuntu,cuda,cudnn,caffe,tensorflow,ROS
增强学习Reinforcement Learning经典算法梳理2：蒙特卡洛方法
增强学习Reinforcement Learning经典算法梳理3：TD方法
ROS相关：使用rospy 编写ros程序并使用rosbag存储数据
DRL前沿之：End to End Learning for Self-Driving Cars
DRL前沿之：Hierarchical Deep Reinforcement Learning
DRL前沿之：End to End Learning for Self-Driving Cars
增强学习Reinforcement Learning经典算法梳理1：policy and value iteration
Paper Reading 2:Human-level control through deep reinforcement learning
用Tensorflow基于Deep Q Learning DQN 玩Flappy Bird
Paper Reading 3:Continuous control with Deep Reinforcement Learning
增强学习Reinforcement Learning经典算法梳理3：TD方法