Regularization of inverse visual problems involving discontinuities
IEEE Transactions on Pattern Analysis and Machine Intelligence
Model-based recognition in robot vision
ACM Computing Surveys (CSUR)
Efficient algorithms for finding maximum matching in graphs
ACM Computing Surveys (CSUR)
Proceedings of the seventh international conference (1990) on Machine learning
Computational strategies for object recognition
ACM Computing Surveys (CSUR)
Characterization of Signals from Multiscale Edges
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic programming of behavior-based robots using reinforcement learning
Artificial Intelligence
Technical Note: \cal Q-Learning
Machine Learning
Learning to predict in uncertain continuous tasks
ML92 Proceedings of the ninth international workshop on Machine learning
Derivational Analogy in PRODIGY: Automating Case Acquisition, Storage, and Utilization
Machine Learning - Special issue on case-based reasoning
Reinforcement learning with replacing eligibility traces
Machine Learning - Special issue on reinforcement learning
A Graduated Assignment Algorithm for Graph Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Teaching Strategy for Memory-Based Control
Artificial Intelligence Review - Special issue on lazy learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
The Elements of Artificial Intelligence Using Common LISP
The Elements of Artificial Intelligence Using Common LISP
Tracking Deformable Objects in the Plane Using an Active Contour Model
IEEE Transactions on Pattern Analysis and Machine Intelligence
Finite-Element Methods for Active Contour Models and Balloons for 2-D and 3-D Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Composing Functions to Speed up Reinforcement Learning in a Changing World
ECML '98 Proceedings of the 10th European Conference on Machine Learning
Theoretical Results on Reinforcement Learning with Temporally Abstract Options
ECML '98 Proceedings of the 10th European Conference on Machine Learning
Using a Case Base of Surfaces to Speed-Up Reinforcement Learning
ICCBR '97 Proceedings of the Second International Conference on Case-Based Reasoning Research and Development
Similarity Metrics: A Formal Unification of Cardinal and Non-Cardinal Similarity Measures
ICCBR '97 Proceedings of the Second International Conference on Case-Based Reasoning Research and Development
A symbol's role in learning low-level control functions
A symbol's role in learning low-level control functions
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
Hierarchical solution of Markov decision processes using macro-actions
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
Flexible decomposition algorithms for weakly coupled Markov decision problems
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
Behavior transfer for value-function-based reinforcement learning
Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems
Accelerating autonomous learning by using heuristic selection of actions
Journal of Heuristics
Synthesis of strategies from interaction traces
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 2
The Role of Anticipation in the Emergence of Language
Anticipatory Behavior in Adaptive Learning Systems
Learning Multi-dimensional Functions: Gas Turbine Engine Modeling
PKDD 2007 Proceedings of the 11th European conference on Principles and Practice of Knowledge Discovery in Databases
Learning Representation and Control in Markov Decision Processes: New Frontiers
Foundations and Trends® in Machine Learning
Improving Reinforcement Learning by Using Case Based Heuristics
ICCBR '09 Proceedings of the 8th International Conference on Case-Based Reasoning: Case-Based Reasoning Research and Development
Value functions for RL-based behavior transfer: a comparative study
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Journal of Artificial Intelligence Research
Transfer Learning for Reinforcement Learning Domains: A Survey
The Journal of Machine Learning Research
Case-Based Multiagent Reinforcement Learning: Cases as Heuristics for Selection of Actions
Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
Using cases as heuristics in reinforcement learning: a transfer learning application
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Hi-index | 0.00 |
This paper discusses a system that accelerates reinforcement learning by using transfer from related tasks. Without such transfer, even if two tasks are very similar at some abstract level, an extensive re-learning effort is required. The system achieves much of its power by transferring parts of previously learned solutions rather than a single complete solution. The system exploits strong features in the multi-dimensional function produced by reinforcement learning in solving a particular task. These features are stable and easy to recognize early in the learning process. They generate a partitioning of the state space and thus the function. The partition is represented as a graph. This is used to index and compose functions stored in a case base to form a close approximation to the solution of the new task. Experiments demonstrate that function composition often produces more than an order of magnitude increase in learning rate compared to a basic reinforcement learning algorithm.