The Complexity of Decentralized Control of Markov Decision Processes
Mathematics of Operations Research
Transition-independent decentralized markov decision processes
AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
The complexity of multiagent systems: the price of silence
AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
Approximate Solutions for Partially Observable Stochastic Games with Common Payoffs
AAMAS '04 Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 1
Collaborative Multiagent Reinforcement Learning by Payoff Propagation
The Journal of Machine Learning Research
Letting loose a SPIDER on a network of POMDPs: generating quality guaranteed policies
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
Decentralised coordination of low-power embedded devices using the max-sum algorithm
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 2
Not all agents are equal: scaling up distributed POMDPs for agent networks
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 1
Exploiting locality of interaction in factored Dec-POMDPs
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 1
Formal models and algorithms for decentralized decision making under uncertainty
Autonomous Agents and Multi-Agent Systems
Constraint-based dynamic programming for decentralized POMDPs with structured interactions
Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
Networked distributed POMDPs: a synthesis of distributed constraint optimization and POMDPs
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 1
Efficient solution algorithms for factored MDPs
Journal of Artificial Intelligence Research
Optimal and approximate Q-value functions for decentralized POMDPs
Journal of Artificial Intelligence Research
Computing factored value functions for policies in structured MDPs
IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
Transfer Learning for Reinforcement Learning Domains: A Survey
The Journal of Machine Learning Research
Bounded approximate decentralised coordination via the max-sum algorithm
Artificial Intelligence
Distributed model shaping for scaling to decentralized POMDPs with hundreds of agents
The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 3
The factored frontier algorithm for approximate inference in DBNs
UAI'01 Proceedings of the Seventeenth conference on Uncertainty in artificial intelligence
Tractable inference for complex stochastic processes
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
Efficient planning for factored infinite-horizon DEC-POMDPs
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume One
Scaling up optimal heuristic search in Dec-POMDPs via incremental expansion
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
Scalable multiagent planning using probabilistic inference
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
Incremental clustering and expansion for faster optimal planning in decentralized POMDPs
Journal of Artificial Intelligence Research
Hi-index | 0.00 |
Dec-POMDPs are a powerful framework for planning in multiagent systems, but are provably intractable to solve. Despite recent work on scaling to more agents by exploiting weak couplings in factored models, scalability for unrestricted subclasses remains limited. This paper proposes a factored forward-sweep policy computation method that tackles the stages of the problem one by one, exploiting weakly coupled structure at each of these stages. To enable the method to scale to many agents, we propose a set of approximations: approximation of stages using a sparse interaction structure, bootstrapping off smaller tasks to compute heuristic payoff functions, and employing approximate inference to estimate required probabilities at each stage and to compute the best decision rules. An empirical evaluation shows that the loss in solution quality due to these approximations is small and that the proposed method achieves unprecedented scalability, solving Dec-POMDPs with hundreds of agents.