Sciweavers

185 search results - page 9 / 37
» Simulation-Based Optimization Algorithms for Finite-Horizon ...
Sort
View
AIPS
2003
13 years 9 months ago
Synthesis of Hierarchical Finite-State Controllers for POMDPs
We develop a hierarchical approach to planning for partially observable Markov decision processes (POMDPs) in which a policy is represented as a hierarchical finite-state control...
Eric A. Hansen, Rong Zhou
ICTAI
2007
IEEE
14 years 1 months ago
Multi-criteria Decision Making for Local Coordination in Multi-agent Systems
Unlike mono-agent systems, multi-agent planing addresses the problem of resolving conflicts between individual and group interests. In this paper, we are using a Decentralized Ve...
Matthieu Boussard, Maroua Bouzid, Abdel-Illah Moua...
ICML
1994
IEEE
13 years 11 months ago
Markov Games as a Framework for Multi-Agent Reinforcement Learning
In the Markov decision process (MDP) formalization of reinforcement learning, a single adaptive agent interacts with an environment defined by a probabilistic transition function....
Michael L. Littman
AAAI
2011
12 years 7 months ago
Policy Gradient Planning for Environmental Decision Making with Existing Simulators
In environmental and natural resource planning domains actions are taken at a large number of locations over multiple time periods. These problems have enormous state and action s...
Mark Crowley, David Poole
AAAI
1994
13 years 9 months ago
Acting Optimally in Partially Observable Stochastic Domains
In this paper, we describe the partially observable Markov decision process pomdp approach to nding optimal or near-optimal control strategies for partially observable stochastic ...
Anthony R. Cassandra, Leslie Pack Kaelbling, Micha...