English
Related papers

Related papers: HSVI can solve zero-sum Partially Observable Stoch…

200 papers

In this paper, we consider two-player zero-sum matrix and stochastic games and develop learning dynamics that are payoff-based, convergent, rational, and symmetric between the two players. Specifically, the learning dynamics for matrix…

Machine Learning · Computer Science 2024-09-06 Zaiwei Chen , Kaiqing Zhang , Eric Mazumdar , Asuman Ozdaglar , Adam Wierman

We consider zero-sum stochastic games with perfect information and finitely many states and actions. The payoff is computed by a function which associates to each infinite sequence of states and actions a real number. We prove that if the…

Computer Science and Game Theory · Computer Science 2022-03-29 Hugo Gimbert , Edon Kelmendi

We analyze best response dynamics for finding a Nash equilibrium of an infinite horizon zero-sum stochastic linear quadratic dynamic game (LQDG) with partial and asymmetric information. We derive explicit expressions for each player's best…

Systems and Control · Electrical Eng. & Systems 2025-09-03 Yuxiang Guan , Iman Shames , Tyler H. Summers

Quantitative games are two-player zero-sum games played on directed weighted graphs. Total-payoff games (that can be seen as a refinement of the well-studied mean-payoff games) are the variant where the payoff of a play is computed as the…

Computer Science and Game Theory · Computer Science 2015-07-15 Thomas Brihaye , Gilles Geeraerts , Axel Haddad , Benjamin Monmege

The Partially Observable Markov Decision Process has long been recognized as a rich framework for real-world planning and control problems, especially in robotics. However exact solutions in this framework are typically computationally…

Artificial Intelligence · Computer Science 2011-10-05 J. Pineau , G. Gordon , S. Thrun

We introduce two-level discounted games played by two players on a perfect-information stochastic game graph. The upper level game is a discounted game and the lower level game is an undiscounted reachability game. Two-level games model…

Logic in Computer Science · Computer Science 2010-06-09 Krishnendu Chatterjee , Rupak Majumdar

Markov Decision Processes (MDPs) are stochastic optimization problems that model situations where a decision maker controls a system based on its state. Partially observed Markov decision processes (POMDPs) are generalizations of MDPs where…

Optimization and Control · Mathematics 2019-03-26 Victor Cohen , Axel Parmentier

We consider two-player partial-observation stochastic games on finite-state graphs where player 1 has partial observation and player 2 has perfect observation. The winning condition we study are \omega-regular conditions specified as parity…

Logic in Computer Science · Computer Science 2014-01-15 Krishnendu Chatterjee , Laurent Doyen , Sumit Nain , Moshe Y. Vardi

In this paper, we study nonzero-sum separable games, which are continuous games whose payoffs take a sum-of-products form. Included in this subclass are all finite games and polynomial games. We investigate the structure of equilibria in…

Computer Science and Game Theory · Computer Science 2010-04-26 Noah D. Stein , Asuman Ozdaglar , Pablo A. Parrilo

Reward optimization in fully observable Markov decision processes is equivalent to a linear program over the polytope of state-action frequencies. Taking a similar perspective in the case of partially observable Markov decision processes…

Machine Learning · Computer Science 2022-05-30 Johannes Müller , Guido Montúfar

Stochastic games are a classical model in game theory in which two opponents interact and the environment changes in response to the players' behavior. The central solution concepts for these games are the discounted values and the value,…

Optimization and Control · Mathematics 2019-12-12 Miquel Oliu-Barton

The classical, complete-information two-player games assume that the problem data (in particular the payoff matrix) is known exactly by both players. In a now famous result, Nash has shown that any such game has an equilibrium in mixed…

Computer Science and Game Theory · Computer Science 2015-12-11 Nicolas Loizou

Planning under uncertainty is critical to robotics. The Partially Observable Markov Decision Process (POMDP) is a mathematical framework for such planning problems. It is powerful due to its careful quantification of the non-deterministic…

Robotics · Computer Science 2021-07-19 Hanna Kurniawati

We present a robust framework with computational algorithms to support decision makers in sequential games. Our framework includes methods to solve games with complete information, assess the robustness of such solutions and, finally,…

Computation · Statistics 2024-02-22 Tahir Ekin , Roi Naveiro , Alberto Torres-Barrán , David Ríos-Insua

We present a fast numerical algorithm for large scale zero-sum stochastic games with perfect information, which combines policy iteration and algebraic multigrid methods. This algorithm can be applied either to a true finite state space…

Optimization and Control · Mathematics 2015-03-19 Marianne Akian , Sylvie Detournay

The Common Information (CI) approach provides a systematic way to transform a multi-agent stochastic control problem to a single-agent partially observed Markov decision problem (POMDP) called the coordinator's POMDP. However, such a POMDP…

Artificial Intelligence · Computer Science 2023-04-11 Dengwang Tang , Ashutosh Nayyar , Rahul Jain

In this paper infinite horizon optimal control problems for nonlinear high-dimensional dynamical systems are studied. Nonlinear feedback laws can be computed via the value function characterized as the unique viscosity solution to the…

Optimization and Control · Mathematics 2016-02-22 Alessandro Alla , Maurizio Falcone , Stefan Volkwein

Partially Observable Markov Decision Process (POMDP) is a framework applicable to many real world problems. In this work, we propose an approach to solve POMDPs with multimodal belief by relying on a policy that solves the fully observable…

Machine Learning · Computer Science 2022-07-26 András Attila Sulyok , Kristóf Karacs

We prove that zero-sum Dynkin games in continuous time with partial and asymmetric information admit a value in randomised stopping times when the stopping payoffs of the players are general \cadlag measurable processes. As a by-product of…

Probability · Mathematics 2022-06-08 Tiziano De Angelis , Nikita Merkulov , Jan Palczewski

Recent superhuman results in games have largely been achieved in a variety of zero-sum settings, such as Go and Poker, in which agents need to compete against others. However, just like humans, real-world AI systems have to coordinate and…

Artificial Intelligence · Computer Science 2019-12-06 Adam Lerer , Hengyuan Hu , Jakob Foerster , Noam Brown