Sciweavers

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

14

AAAI
2010

favoriteEmaildiscussreport

173views Intelligent Agents» more AAAI 2010»

Integrating Sample-Based Planning and Model-Based Reinforcement Learning

13 years 5 months ago

Integrating Sample-Based Planning and Model-Based Reinforcement Learning

Download paul.rutgers.edu

Recent advancements in model-based reinforcement learning have shown that the dynamics of many structured domains (e.g. DBNs) can be learned with tractable sample complexity, despite their exponentially large state spaces. Unfortunately, these algorithms all require access to a planner that computes a near optimal policy, and while many traditional MDP algorithms make this guarantee, their computation time grows with the number of states. We show how to replace these over-matched planners with a class of sample-based planners--whose computation time is independent of the number of states--without sacrificing the sampleefficiency guarantees of the overall learning algorithms. To do so, we define sufficient criteria for a sample-based planner to be used in such a learning system and analyze two popular sample-based approaches from the literature. We also introduce our own sample-based planner, which combines the strategies from these algorithms and still meets the criteria for integrati...

Thomas J. Walsh, Sergiu Goschin, Michael L. Littma

Real-time Traffic

AAAI 2010 | Computation Time | Intelligent Agents | Sample-based | Sample-based Planner |

claim paper

Related Content

» Nonparametric ModelBased Reinforcement Learning

» ModelBased Bayesian Reinforcement Learning in Large Structured Domains

» ModelBased Reinforcement Learning in a Complex Domain

» Smarter Sampling in ModelBased Bayesian Reinforcement Learning

» Automatic Feature Selection for ModelBased Reinforcement Learning in Factored MDPs

» Learning Methods to Generate Good Plans Integrating HTN Learning and Reinforcement Learnin...

» AlgorithmDirected Exploration for ModelBased Reinforcement Learning in Factored MDPs

» Learning the structure of Factored Markov Decision Processes in reinforcement learning pro...

» Exploring Continuous Action Spaces with Diffusion Trees for Reinforcement Learning

Post Info
More Details (n/a)

Added	29 Oct 2010
Updated	29 Oct 2010
Type	Conference
Year	2010
Where	AAAI
Authors	Thomas J. Walsh, Sergiu Goschin, Michael L. Littman

Comments (0)