Sciweavers

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

14

ICML
2002
IEEE

favoriteEmaildiscussreport

146views Machine Learning» more ICML 2002»

Hierarchically Optimal Average Reward Reinforcement Learning

14 years 5 months ago

Hierarchically Optimal Average Reward Reinforcement Learning

Download www.cs.ualberta.ca

Two notions of optimality have been explored in previous work on hierarchical reinforcement learning (HRL): hierarchical optimality, or the optimal policy in the space defined by a task hierarchy, and a weaker local model called recursive optimality. In this paper, we introduce two new average-reward HRL algorithms for finding hierarchically optimal policies. We compare them to our previously reported algorithms for computing recursively optimal policies, using a grid-world taxi problem and a more real-world AGV scheduling problem. The new algorithms are based on a three-part value function decomposition proposed recently by Andre and Russell, which generalizes Dietterich's MAXQ value function decomposition. A key difference between the algorithms proposed in this paper and our previous work is that there is only a single global gain (average reward), instead of a gain for each subtask. Our results show the new average-reward algorithms have better performance than both the previ...

Mohammad Ghavamzadeh, Sridhar Mahadevan

Real-time Traffic

Average-reward Hrl Algorithms | Hierarchical Optimal Algorithms | ICML 2002 | Machine Learning | Optimal Policies |

claim paper

Related Content

» ContinuousTime Hierarchical Reinforcement Learning

» Sensitive Discount Optimality Unifying Discounted and Average Reward Reinforcement Learnin...

» Scaling ModelBased AverageReward Reinforcement Learning for Product Delivery

» Reinforcement Learning for Average Reward ZeroSum Games

» ModelBased Average Reward Reinforcement Learning

» The Optimal Reward Baseline for GradientBased Reinforcement Learning

» Reinforcement Learning in POMDPs via Direct Gradient Ascent

» RMAX A General Polynomial Time Algorithm for NearOptimal Reinforcement Learning

» Exploiting Multiple Secondary Reinforcers in Policy Gradient Reinforcement Learning

Post Info
More Details (n/a)

Added	17 Nov 2009
Updated	17 Nov 2009
Type	Conference
Year	2002
Where	ICML
Authors	Mohammad Ghavamzadeh, Sridhar Mahadevan

Comments (0)