Temporal difference learning and TD-Gammon
Communications of the ACM
Continuous case-based reasoning
Artificial Intelligence
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Learning to Predict by the Methods of Temporal Differences
Machine Learning
INRECA: A Seamlessly Integrated System Based on Inductive Inference and Case-Based Reasoning
ICCBR '95 Proceedings of the First International Conference on Case-Based Reasoning Research and Development
VQQL. Applying Vector Quantization to Reinforcement Learning
RoboCup-99: Robot Soccer World Cup III
Using Reinforcement Learning for Similarity Assessment in Case-Based Systems
IEEE Intelligent Systems
An Analysis of Case-Based Value Function Approximation by Approximating State Transition Graphs
ICCBR '07 Proceedings of the 7th international conference on Case-Based Reasoning: Case-Based Reasoning Research and Development
ECCBR '08 Proceedings of the 9th European conference on Advances in Case-Based Reasoning
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
Maintenance by a Committee of Experts: The MACE Approach to Case-Base Maintenance
ICCBR '09 Proceedings of the 8th International Conference on Case-Based Reasoning: Case-Based Reasoning Research and Development
RETALIATE: learning winning policies in first-person shooter games
IAAI'07 Proceedings of the 19th national conference on Innovative applications of artificial intelligence - Volume 2
Transfer learning in real-time strategy games using hybrid CBR/RL
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
The virtue of reward: performance, reinforcement and discovery in case-based reasoning
ICCBR'05 Proceedings of the 6th international conference on Case-Based Reasoning Research and Development
CBR for state value function approximation in reinforcement learning
ICCBR'05 Proceedings of the 6th international conference on Case-Based Reasoning Research and Development
Integrated learning for goal-driven autonomy
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three
| Hi-index | 0.00 |
In this paper we present an approach for reducing the memory footprint requirement of temporal difference methods in which the set of states is finite. We use case-based generalization to group the states visited during the reinforcement learning process. We follow a lazy learning approach; cases are grouped in the order in which they are visited. Any new state visited is assigned to an existing entry in the Q-table provided that a similar state has been visited before. Otherwise a new entry is added to the Q-table. We performed experiments on a turn-based game where actions have non-deterministic effects and might have long term repercussions on the outcome of the game. The main conclusion from our experiments is that by using case-based generalization, the size of the Q-table can be substantially reduced while maintaining the quality of the RL estimates.