Sciweavers

Share
135 search results - page 2 / 27
» Relational Partially Observable MDPs
Sort
View
UAI
2000
9 years 1 months ago
PEGASUS: A policy search method for large MDPs and POMDPs
We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a mo...
Andrew Y. Ng, Michael I. Jordan
AI
2011
Springer
8 years 3 months ago
Decentralized MDPs with sparse interactions
In this work, we explore how local interactions can simplify the process of decision-making in multiagent systems, particularly in multirobot problems. We review a recent decision-...
Francisco S. Melo, Manuela M. Veloso
AAAI
2011
8 years 1 days ago
Linear Dynamic Programs for Resource Management
Sustainable resource management in many domains presents large continuous stochastic optimization problems, which can often be modeled as Markov decision processes (MDPs). To solv...
Marek Petrik, Shlomo Zilberstein
JAIR
2016
3 years 8 months ago
Optimally Solving Dec-POMDPs as Continuous-State MDPs
Optimally solving decentralized partially observable Markov decision processes (Dec-POMDPs) is a hard combinatorial problem. Current algorithms search through the space of full hi...
Jilles Steeve Dibangoye, Christopher Amato, Olivie...
NIPS
2003
9 years 1 months ago
Bounded Finite State Controllers
We describe a new approximation algorithm for solving partially observable MDPs. Our bounded policy iteration approach searches through the space of bounded-size, stochastic fini...
Pascal Poupart, Craig Boutilier
books