Deep Reinforcement Learning for an Anthropomorphic Robotic Arm Under Sparse Reward Tasks.
Hao ChengFeng DuanHaosi ZhengPublished in: ICIRA (2) (2021)
Keyphrases
- reinforcement learning
- robotic arm
- transfer learning
- function approximation
- motion planning
- state space
- degrees of freedom
- robot arm
- master slave
- model free
- reinforcement learning algorithms
- learning algorithm
- dynamic programming
- markov decision processes
- reward function
- learning agent
- optimal policy
- real time
- human arm
- humanoid robot
- optimal control
- path planning
- computer graphics
- three dimensional
- machine learning