paper-with-me

Papers

Imprecise Probabilities Meet Partial Observability: Game Semantics for Robust POMDPs

2024-05-08 · Eline M. Bovy, Marnix Suilen, Sebastian Junges, Nils Jansen

Partially observable Markov decision processes (POMDPs) rely on the key assumption that probability distributions are precisely known. Robust POMDPs (RPOMDPs) alleviate this concern by defining imprecise probabilities, referred to as uncertainty sets. While robust MDPs have been studied extensively, work on RPOMDPs is limited and primarily focuses on algorithmic solution methods. We expand the theoretical understanding of RPOMDPs by showing that 1) different assumptions on the uncertainty sets affect optimal policies and values; 2) RPOMDPs have a partially observable stochastic game (POSG) semantic; and 3) the same RPOMDP with different assumptions leads to semantically different POSGs and, thus, different policies and values. These novel semantics for RPOMDPs give access to results for POSGs, studied in game theory; concretely, we show the existence of a Nash equilibrium. Finally, we classify the existing RPOMDP literature using our semantics, clarifying under which uncertainty assumptions these existing works operate.

📄 PDF Abstract BibTeX arXiv:2405.04941

Code (1)

lava-lab/rpomdp_game_semantics_value_functions 공식 구현

Similar Papers 제목 키워드 기반

Graph Constrained Reinforcement Learning for Natural Language Action Spaces

2020-01-23 · ICLR 2020 1 · Prithviraj Ammanabrolu, Matthew Hausknecht

Interactive Fiction games are text-based simulations in which an agent interacts with the world purely through natural language. They are ideal environments for studying how to extend reinforcement learning agents to mee…

Action GenerationNatural Language Understandingreinforcement-learningReinforcement Learning+2

Robust Active Measuring under Model Uncertainty

2023-12-18 · Merlijn Krale, Thiago D. Simão, Jana Tumova, Nils Jansen

Partial observability and uncertainty are common problems in sequential decision-making that particularly impede the use of formal models such as Markov decision processes (MDPs). However, in practice, agents may be able…

Decision MakingmodelSequential Decision Making

Reinforcement learning for Quantum Tiq-Taq-Toe

2024-11-10 · Catalin-Viorel Dinu, Thomas Moerland

Quantum Tiq-Taq-Toe is a well-known benchmark and playground for both quantum computing and machine learning. Despite its popularity, no reinforcement learning (RL) methods have been applied to Quantum Tiq-Taq-Toe. Altho…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains

2025-07-31 · Ruo Yu Tao, Kaicheng Guo, Cameron Allen, George Konidaris arxiv

Mitigating partial observability is a necessary but challenging task for general reinforcement learning algorithms. To improve an algorithm's ability to mitigate partial observability, researchers need comprehensive benc…

General Reinforcement Learning

Ms. Pac-Man Versus Ghost Team CIG 2016 Competition

2016-09-08 · Piers R. Williams, Diego Perez-Liebana, Simon M. Lucas

This paper introduces the revival of the popular Ms. Pac-Man Versus Ghost Team competition. We present an updated game engine with Partial Observability constraints, a new Multi-Agent Systems approach to developing Ghost…