Defeating the Non-stationary Opponent Using Deep Reinforcement Learning and Opponent Modeling.
Qian YaoXinli XiongPeng WangYongjie WangPublished in: CollaborateCom (2) (2023)
Keyphrases
- non stationary
- opponent modeling
- imperfect information
- reinforcement learning
- game playing
- game theoretic
- adaptive algorithms
- game tree search
- autoregressive
- game theory
- agent receives
- learning algorithm
- multi agent
- white noise
- empirical mode decomposition
- game tree
- biomedical signals
- hidden markov models
- learning process
- state space
- search algorithm
- financial time series
- regular expressions
- optimal policy