Efficient approximate planning in continuous space Markovian Decision Problems

Authors:
Csaba Szepesvári
Affiliations:
Mindmaker Ltd., Konkoly‐Thege M. u. 29‐33, 1121, Budapest, Hungary E‐mail: szepes@mindmaker.hu
Venue:
AI Communications
Year:
2001

Citing 5
Cited 3

Dynamic programming: deterministic and stochastic models

Dynamic programming: deterministic and stochastic models
The complexity of dynamic programming

Journal of Complexity
Markov Decision Processes: Discrete Stochastic Dynamic Programming

Markov Decision Processes: Discrete Stochastic Dynamic Programming
A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes

IJCAI '99 Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence
Dynamic Programming

Dynamic Programming

Autonomous behaviors for interactive vehicle animations

SCA '04 Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation
Autonomous behaviors for interactive vehicle animations

Graphical Models - Special issue on SCA 2004
Finite-Time Bounds for Fitted Value Iteration

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

Monte‐Carlo planning algorithms for planning in continuous state‐space, discounted Markovian Decision Problems (MDPs) having a smooth transition law and a finite action space are considered. We prove various polynomial complexity results for the considered algorithms, improving upon several known bounds.