On Passivity and Reinforcement Learning in Finite Games.
Bolin GaoLacra PavelPublished in: CDC (2018)
Keyphrases
- reinforcement learning
- action sets
- learning agents
- state and action spaces
- function approximation
- reinforcement learning agents
- state space
- video games
- computer games
- game theory
- multiagent learning
- markov decision processes
- finite number
- nash equilibrium
- model free
- multi agent
- game theoretic
- reinforcement learning algorithms
- coalitional games
- neural network
- game design
- learning algorithm
- machine learning
- search algorithm
- temporal difference
- multiagent systems
- nash equilibria
- perfect information
- reinforcement learning methods
- sliding mode
- policy search
- state abstraction
- learning process
- human computation
- dynamic programming
- optimal control
- optimal policy
- stochastic games
- action space
- markov decision process
- transfer learning
- decision problems
- game playing