Grasp for Stacking via Deep Reinforcement Learning.
Junhao ZhangWei ZhangRan SongLin MaYibin LiPublished in: ICRA (2020)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- reinforcement learning algorithms
- temporal difference
- learning process
- robotic control
- state space
- optimal policy
- tabu search
- control problems
- ensemble learning
- direct policy search
- learning algorithm
- transition model
- model free
- combining multiple
- learning problems
- transfer learning
- dynamic programming
- multi agent
- learning tasks
- deep learning
- temporal difference learning
- policy search
- decision trees