Deep Reinforcement Learning Based Intelligent Decision Making for Two-player Sequential Game with Uncertain Irrational Player.
Zejian ZhouHao XuPublished in: SSCI (2019)
Keyphrases
- intelligent decision making
- repeated games
- reinforcement learning
- multi player
- incomplete information
- decision making
- imperfect information
- perfect information
- game playing
- game play
- human players
- reinforcement learning algorithms
- card game
- nash equilibrium
- stochastic games
- game theoretic
- computational intelligence
- average reward
- online game
- systems engineering
- function approximation
- nash equilibria
- two player games
- fuzzy logic
- board game
- markov decision processes
- educational games
- game players
- video games
- temporal difference
- agent model
- computer games
- model free
- learning algorithm
- game theory
- optimal policy
- machine learning
- game tree
- evaluation function
- data analysis
- multi agent
- solution concepts
- single agent
- neural network
- boolean games
- pure nash equilibria
- learning agents
- human computation
- optimal strategy
- software engineering
- game mechanics
- computer poker
- normal form games