I4R: Promoting Deep Reinforcement Learning by the Indicator for Expressive Representations.
Xufang LuoQi MengDi HeWei ChenYunhong WangPublished in: IJCAI (2020)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- dynamic programming
- function approximators
- robotic control
- temporal difference learning
- state space
- information systems
- optimal policy
- probability distribution
- model free
- temporal difference
- representation scheme
- artificial intelligence
- machine learning
- multi agent reinforcement learning
- databases