Off-Policy Reinforcement Learning for Partially Unknown Nonzero-Sum Games.
Qichao ZhangDongbin ZhaoSibo ZhangPublished in: ICONIP (1) (2017)
Keyphrases
- reinforcement learning
- action sets
- learning agents
- function approximation
- state space
- video games
- computer games
- reinforcement learning algorithms
- game theoretic
- nash equilibrium
- reinforcement learning agents
- learning algorithm
- machine learning
- learning problems
- objective function
- initially unknown
- weighted majority
- multiagent learning
- game design
- game playing
- temporal difference
- neural network
- games played
- model free
- game play
- educational games
- optimal control
- markov decision processes
- learning process
- multi agent