IROS22-DMMAS_paper_7852.pdf

N/A

Toward Capability-Aware Cooperation for Decentralized Planning Charles Jin, Zhang-Wei Hong, Martin Rinard1 Abstract— Many works cast the problem of decentralized multi-agent planning aims to coordinate a team of agents multi-agent cooperation as fundamentally one of misspecified to maximize a joint utility function. Classic works employ (or incorrectly inferred) goals. In this work, we show that heuristic search algorithms on each agent to maximize the challenges can also arise naturally due a difference in capa-…

saved by

• Judah Newman

related reading

• pdfopenreview.net
• [2206.12765] Generalized Beliefs for Cooperative AIarxiv.org
• [2605.22748] Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learningarxiv.org
• Reinforcement Learning in Newcomblike Problemsproceedings.neurips.cc
• c21f4ce780c5c9d774f79841b81fdc6d-Paper.pdfproceedings.neurips.cc
• [2602.11865] Intelligent AI Delegationarxiv.org
• [2603.21972] Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipearxiv.org
• [2410.00079] Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interfacearxiv.org
• Exploration for the Efficient Deployment of Reinforcement Learning Agentsopenreview.net
• [2606.05555] Representation Learning Enables Scalable Multitask Deep Reinforcement Learningarxiv.org
• PhD_thesis_Shirley_Wu_final.pdfcs.stanford.edu
• Deep Reinforcement Learning from Human Preferencesproceedings.neurips.cc