Stopping Criteria for Value Iteration on Stochastic Games with Quantitative Objectives.
Jan KretínskýTobias MeggendorferMaximilian WeiningerPublished in: CoRR (2023)
Keyphrases
- stochastic games
- stopping criteria
- markov decision processes
- average reward
- infinite horizon
- state space
- policy iteration
- nash equilibria
- reinforcement learning algorithms
- optimal policy
- reinforcement learning
- finite state
- stopping criterion
- long run
- nash equilibrium
- clustering algorithm
- dynamic programming
- partially observable
- learning automata
- repeated games
- heuristic search
- model free
- average cost
- markov decision process
- multi agent
- sufficient conditions
- markov chain
- decision theoretic
- cost function
- search algorithm
- game theory