Adaptive deep reinforcement learning for non-stationary environments.
Jin ZhuYutong WeiYu KangXiaofeng JiangGeir E. DullerudPublished in: Sci. China Inf. Sci. (2022)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- markov decision process
- adaptive learning
- non stationary
- adaptive algorithms
- function approximation
- artificial intelligence
- learning algorithm
- dynamic programming
- social networks
- practical problems
- learning capabilities
- machine learning
- multi agent
- image sequences
- class imbalance
- model free