Heuristic Search Value Iteration for Zero-Sum Stochastic Games.
Olivier BuffetJilles DibangoyeAbdallah SaffidineVincent ThomasPublished in: IEEE Trans. Games (2021)
Keyphrases
- stochastic games
- heuristic search
- markov decision processes
- state space
- search algorithm
- nash equilibria
- games with incomplete information
- reinforcement learning algorithms
- search space
- path finding
- multiagent reinforcement learning
- single agent
- multi agent
- planning problems
- average reward
- learning automata
- reinforcement learning
- repeated games
- optimal policy
- finite state
- nash equilibrium
- orders of magnitude
- infinite horizon
- robust optimization
- dynamic programming
- learning agent
- incomplete information
- game theory
- average cost
- markov decision process
- state variables
- np hard
- multi agent systems