829 search results - page 114 / 166 » A time aggregation approach to Markov decision processes |
175
click to vote
ICML
2007
IEEE
16 years 7 months ago
2007
IEEE
This paper introduces a new approach to actionvalue function approximation by learning basis functions from a spectral decomposition of the state-action manifold. This paper exten...
166
click to vote
ECML
2007
Springer
16 years 10 days ago
2007
Springer
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...
176
click to vote
AI
2006
Springer
15 years 10 months ago
2006
Springer
Abstract. Current point-based planning algorithms for solving partially observable Markov decision processes (POMDPs) have demonstrated that a good approximation of the value funct...
136
click to vote
AAAI
2007
15 years 8 months ago
2007
A new spectral approach to value function approximation has recently been proposed to automatically construct basis functions from samples. Global basis functions called proto-val...
154
click to vote
NIPS
2001
15 years 7 months ago
2001
We present a principled and efficient planning algorithm for cooperative multiagent dynamic systems. A striking feature of our method is that the coordination and communication be...