Attentive Update of Multi-Critic for Deep Reinforcement Learning.
Qing LiWengang ZhouYun ZhouHouqiang LiPublished in: ICME (2021)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- reinforcement learning algorithms
- actor critic
- state space
- markov decision processes
- learning algorithm
- learning process
- visual attention
- policy gradient
- optimal control
- model free
- temporal difference learning
- natural actor critic
- robotic control
- real time
- action space
- deep learning
- dynamical systems
- markov chain
- dynamic programming
- data sets