Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

12

ICML
1996
IEEE

favoriteEmaildiscussreport

162views Machine Learning» more ICML 1996»

Sensitive Discount Optimality: Unifying Discounted and Average Reward Reinforcement Learning

14 years 5 months ago

Sensitive Discount Optimality: Unifying Discounted and Average Reward Reinforcement Learning

Download reference.kfupm.edu.sa

Research in reinforcementlearning (RL)has thus far concentrated on two optimality criteria: the discounted framework, which has been very well-studied, and the averagereward framework, in which interest is rapidly increasing. In this paper, we present a framework called sensitive discount optimality which o ers an elegant way of linking these two paradigms. Although sensitive discount optimality has been well studied in dynamic programming, with several provably convergent algorithms, it has not received any attention in RL. This framework is based on studying the propertiesof the expected

Sridhar Mahadevan

Real-time Traffic

Averagereward Framework | ICML 1996 | Machine Learning | Optimality Criteria | Sensitive Discount Optimality |

claim paper

Related Content

» ContinuousTime Hierarchical Reinforcement Learning

» Hierarchically Optimal Average Reward Reinforcement Learning

» ModelBased Average Reward Reinforcement Learning

» The Optimal Reward Baseline for GradientBased Reinforcement Learning

» Bounded Parameter Markov Decision Processes with Average Reward Criterion

» Convergence and Divergence in Standard and Averaging Reinforcement Learning

» Nearly optimal explorationexploitation decision thresholds

» Using Reinforcement Learning to Spider the Web Efficiently

» Efficient QoS Provisioning for Adaptive Multimedia in Mobile Communication Networks by Rei...

Post Info
More Details (n/a)

Added	17 Nov 2009
Updated	17 Nov 2009
Type	Conference
Year	1996
Where	ICML
Authors	Sridhar Mahadevan

Comments (0)