Rényi State Entropy for Exploration Acceleration in Reinforcement Learning.
Mingqi YuanMan-On PunDong WangPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- state space
- function approximation
- neural network
- shannon entropy
- dynamic programming
- transfer learning
- action selection
- autonomous learning
- multi agent
- learning process
- feature selection
- image registration
- optimal policy
- real world
- markov decision process
- state abstraction
- transition model
- database