Workshop on Stochastic Games Directory
Approximating an Absorbing Game Using Collections of Games
Computing Subgame Perfect Equilibrium Payoffs
Distributed Asynchronous Stochastic Games
Percolation Games: A bridge between Game Theory and Analysis
Policy Improvement for Additive Reward additive transition stochastic games with discounted and average payoff
We give a policy improvement algorithm for two person for zero sum stochastic games with additive reward and additive transition in both discounted and Cesaro average payoffs.
Robust optimization in stochastic games
Sequential Optimization of CVaR for MDPs is a Stochastic Game: Existence and Computation of Optimal Policies
We study the problem of Conditional Value at Risk (CVaR) optimization for a finite-state Markov Decision Process (MDP) with total discounted costs and the reduction of this problem to a stochastic game with perfect information. The CVaR optimization problem for a finite and infinite-horizon MDP can be reformulated as a zero-sum stochastic game with a compact state space. This game has the following property: while the second player has perfect information including the knowledge of the decision chosen by the first player at the current time instance, the first player does not directly observe the augmented component of the state and does not know current and past decisions chosen by the second player. By using methods of convex analysis, we show that optimal policies exist for this game, and an optimal policy of the first player optimizes CVaR of the total discounted costs. In addition to proving the existence of optimal policies, we formulate algorithms for their computation and prove convergence.