Partially Observable Stochastic Games

Latest papers

14 papers4 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Reward Objectives for Robust (PO)MDPs: A Law-Preserving Equivalence with (Partially Observable) Games
Oct 19, 2026Durgam Latha, Dion Reji, Dorde Zikelic +1Partially Observable Stochastic Games Robust Partially Observable Markov Decision Processes
Indian Institute of Technology Bombay Mumbai, India · Nanyang Technological University Singapore, Singapore
On Symmetry for Characterizing Agent Heterogeneity in Multi-Agent Systems
Oct 13, 2026Jianhong Wang, Jonathan LawryPartially Observable Stochastic Games Multi-Agent Systems
INFORMED-AI Hub, University of Bristol · School of Engineering Mathematics and Technology, University of Bristol
When Does Opponent Modeling Pay Off? Spatial Inference Stabilises Reinforcement Learning under Partial Observability
Oct 13, 2026Marcel Petran, Stefan EdelkampOpponent Modeling Multi-Agent Reinforcement Learning
Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic
Orchestrating Level- $K$ Policies Against Unknown Opponents in Partially-Observable Dynamic Games
Oct 4, 2026Addison Kalanther, Sanika Bharvirkar, Daniel Bostwick +2Multi-Agent Orchestration Multi-Agent Reinforcement Learning
EECS, University of California, Berkeley, CA, USA · ECE, Johns Hopkins University, Baltimore, MD, USA
Solving Robust POMDPs with Omega-regular Objectives via Partially Observable Stochastic Games
Aug 25, 2026Durgam Latha, Dion Reji, S. Akshay +2Robust Markov Decision Processes Partially Observable Stochastic Games
Indian Institute of Technology Bombay Mumbai, India · Nanyang Technological University Singapore, Singapore
Mobile Target Search with Imperfect Perception: A Partially Observable Stochastic Game Theoretical Approach
Jun 18, 2026Hanzheng Zhang, Shu Liang, Shuyu LiuImperfect-Information Games Game Theory
Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai, China · Department of Control Science and Engineering, Tongji University, Shanghai, China
DNQ: Deep Nash Q-Network for Partially Observable n-Player Games
Jun 4, 2026Qintong Xie, Edward Koh, Xavier Cadet +1Nash Equilibrium Reinforcement Learning
Minimax-Optimal Policy Regret in Partially Observable Markov Games
Jun 1, 2026Raman AroraRegret Minimization in RL Imperfect-Information Games
Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA.
Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
May 7, 2026Philip Jordan, Maryam KamgarpourNash Equilibrium Computation Reinforcement Learning
SYCAMORE, EPFL
Nash Approximation Gap in Truncated Infinite-horizon Partially Observable Markov Games
Apr 6, 2026Lan Sang, Chinmay MaheshwariPartially Observable Stochastic Games Imperfect-Information Games
Applied Mathematics and Statistics at Johns Hopkins University, Baltimore, MD, USA · Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA
Internal State-Based Policy Gradient Methods for Partially Observable Markov Potential Games
Apr 1, 2026Wonseok Yang, Thinh T. DoanNatural Policy Gradient Multi-Agent Reinforcement Learning
University of Texas at Austin, Austin, TX, 78712 USA
SkyNet: Belief-Aware Planning for Partially-Observable Stochastic Games
Mar 29, 2026Adam HailePartially Observable Stochastic Games Imperfect-Information Games
Dwight and Dian Diercks School of Advanced Computing Milwaukee School of Engineering 1025 N Broadway St, Milwaukee, WI 53202
Opponent State Inference Under Partial Observability: An HMM-POMDP Framework for 2026 Formula 1 Energy Strategy
Mar 1, 2026Kalliopi KleisarchakiPartially Observable Stochastic Games Opponent Modeling
Independent Researcher
AIDG: A Formal Decomposition of Information Extraction and Containment Asymmetries in Multi-Turn LLM Dialogue
Feb 19, 2026Adib Sakhawat, Fardeen Sadab, Rakin ShahriarPartially Observable Stochastic Games Multi-Turn Dialogue Evaluation
Department of Computer Science and Engineering, Islamic University of Technology, Dhaka, Bangladesh

Oct 19, 2026J/K move · Enter open · S save

Reward Objectives for Robust (PO)MDPs: A Law-Preserving Equivalence with (Partially Observable) Games

Durgam Latha, Dion Reji, Dorde Zikelic, Shankaranarayanan Krishna

Indian Institute of Technology Bombay Mumbai, India · Nanyang Technological University Singapore, Singapore

Partially Observable Stochastic Games Robust Partially Observable Markov Decision Processes Robust Markov Decision Processes Partially Observable Markov Decision Processes Risk-Sensitive Planning Risk-Sensitive RL

Open paper AskPDF arXiv

Robust partially observable Markov decision processes model agents that act under partial observability while adversarial environment resolves uncertainty in the transition probabilities. Reward objectives such as discounted-sum, long-run average and cumulative reward under finite and infinite horizons allow quantifying the utility of an agent. We consider the problem of solving RPOMDPs under all four reward objectives, where the goal is to decide whether the value of a risk measure with respect to a reward objective exceeds a given threshold. We consider different risk measures, such as (1)~expected value, (2)~mean-variance (MV), (3)~conditional value-at-risk (CVaR), and (4)~entropic risk (ERisk). Our results can be summarized as follows. First, we formalize the class of law-invariant risk measures, that subsume all four risk measures above. Second, we propose a unified framework for solving RPOMDPs with discounted-sum, long-run average and cumulative reward objectives under any law-invariant risk measure, by reducing the problem to solving partially observable stochastic games (POSGs). Our unified framework applies to (s,a)-rectangular RPOMDPs with polytopic uncertainty sets, which we show to be {\em equivalent} to POSGs, for each of the four reward objectives and any law-invariant risk measure. We prove equivalence by designing logspace reductions between the RPOMDP and POSG models, that map strategies to strategies and preserve the distribution of the reward objective, up to a constant rescaling factor. Third, as a corollary, we derive new computational complexity results for R(PO)MDPs and POSGs. In particular, we show that solving (s,a)-rectangular RMDPs is as hard as solving simple stochastic games.