Dual-Critic Deep Reinforcement Learning for Push-Grasping Synergy in Cluttered Environment.
Jiakang ZhongYew Wee WongJiong JinYong SongXianfeng YuanXiaoqi ChenPublished in: ICRA (2024)
Keyphrases
- cluttered environments
- reinforcement learning
- function approximation
- actor critic
- reinforcement learning algorithms
- temporal difference
- policy gradient
- target tracking
- vision system
- challenging problem in computer vision
- model free
- state space
- tracking objects
- optimal control
- optimal policy
- learning algorithm
- markov decision processes
- real time
- dynamic programming
- machine learning