Sciweavers

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

8

AAAI
2006

favoriteEmaildiscussreport

116views Intelligent Agents» more AAAI 2006»

Value-Function-Based Transfer for Reinforcement Learning Using Structure Mapping

13 years 5 months ago

Value-Function-Based Transfer for Reinforcement Learning Using Structure Mapping

Download www.cs.utexas.edu

Transfer learning concerns applying knowledge learned in one task (the source) to improve learning another related task (the target). In this paper, we use structure mapping, a psychological and computational theory about analogy making, to find mappings between the source and target tasks and thus construct the transfer functional automatically. Our structure mapping algorithm is a specialized and optimized version of the structure mapping engine and uses heuristic search to find the best maximal mapping. The algorithm takes as input the source and target task specifications represented as qualitative dynamic Bayes networks, which do not need probability information. We apply this method to the Keepaway task from RoboCup simulated soccer and compare the result from automated transfer to that from handcoded transfer.

Yaxin Liu, Peter Stone

Real-time Traffic

AAAI 2006 | Intelligent Agents | Structure Mapping | Target Task | Transfer Learning Concerns |

claim paper

Related Content

» Multiagent Transfer Learning via AssignmentBased Decomposition

» Direct Policy Search Reinforcement Learning for Robot Control

» Using Homomorphisms to Transfer Options across Continuous Reinforcement Learning Domains

» Skill Acquisition Via Transfer Learning and Advice Taking

» Using Advice to Transfer Knowledge Acquired in One Reinforcement Learning Task to Another

» Probabilistic Policy Reuse for intertask transfer learning

» General Game Learning Using Knowledge Transfer

» Trajectory Optimization using Reinforcement Learning for Map Exploration

» GraphBased Domain Mapping for Transfer Learning in General Games

Post Info
More Details (n/a)

Added	30 Oct 2010
Updated	30 Oct 2010
Type	Conference
Year	2006
Where	AAAI
Authors	Yaxin Liu, Peter Stone

Comments (0)