Accelerating Robot Reinforcement Learning with Samples of Different Simulation Precision.
Yong ZhaoYuanzhao ZhaiJie LuoDawei FengBo DingZhen LiPublished in: HPCC/DSS/SmartCity/DependSys (2021)
Keyphrases
- real robot
- reinforcement learning
- mobile robot
- experimental platform
- data sets
- simulated robot
- robot control
- robotic systems
- path planning
- humanoid robot
- autonomous learning
- mobile robotics
- perceptual aliasing
- high precision
- human robot interaction
- vision system
- obstacle avoidance
- real time
- function approximation
- goal directed
- learning algorithm
- learning process
- active learning
- semi supervised
- simulation model
- optimal policy