Skip to Main content Skip to Navigation
Conference papers

Optimally Solving Two-Agent Decentralized POMDPs Under One-Sided Information Sharing

Yuxuan Xie 1 Jilles Dibangoye 2 Olivier Buffet 3
2 CHROMA - Robots coopératifs et adaptés à la présence humaine en environnements dynamiques
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
3 LARSEN - Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : Optimally solving decentralized partially observable Markov decision processes (Dec-POMDPs) under either full or no information sharing received significant attention in recent years. However, little is known about how partial information sharing affects existing theory and algorithms. This paper addresses this question for a team of two agents, with one-sided information sharing, i.e. both agents have imperfect information about the state of the world, but only one has access to what the other sees and does. From the perspective of a central planner, we show that the original problem can be reformulated into an equivalent information-state Markov decision process and solved as such. Besides, we prove that the optimal value function exhibits a specific form of uniform continuity. We also present heuristic search algorithms utilizing this property and providing the first results for this family of problems.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-03080192
Contributor : Olivier Buffet <>
Submitted on : Thursday, December 17, 2020 - 3:34:49 PM
Last modification on : Monday, December 21, 2020 - 3:02:02 PM

File

xie20a.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03080192, version 1

Citation

Yuxuan Xie, Jilles Dibangoye, Olivier Buffet. Optimally Solving Two-Agent Decentralized POMDPs Under One-Sided Information Sharing. ICML 2020 - 37th International Conference on Machine Learning, Jul 2020, Vienne / Virtual, Austria. ⟨hal-03080192⟩

Share

Metrics

Record views

29

Files downloads

120