Integral Reinforcement Learning for online computation of feedback Nash strategies of nonzero-sum differential games.
Draguna L. VrabieFrank L. LewisPublished in: CDC (2010)
Keyphrases
- reinforcement learning
- equilibrium strategies
- nash equilibrium
- learning agents
- nash equilibria
- game theory
- game theoretic
- cooperative game
- mixed strategy
- online learning
- solution concepts
- real time
- online game
- function approximation
- repeated games
- utility function
- multi agent
- learning algorithm
- stochastic games
- game playing
- objective function
- test beds
- relevance feedback
- action sets
- exploration strategy
- balancing exploration and exploitation
- multi agent reinforcement learning
- multiagent learning
- temporal difference learning
- reinforcement learning algorithms
- model free
- computer games
- state space
- learning environment