New Generation Computing - Selected papers from the international workshop on algorithmic learning theory,1990
The cascade-correlation learning architecture
Advances in neural information processing systems 2
C4.5: programs for machine learning
C4.5: programs for machine learning
Temporal difference learning and TD-Gammon
Communications of the ACM
Failure driven dynamic search control for partial order planners: an explanation based approach
Artificial Intelligence
Machine Learning - special issue on inductive logic programming
Inferring state constraints for domain-independent planning
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Learning action strategies for planning domains
Artificial Intelligence
Using temporal logics to express search control knowledge for planning
Artificial Intelligence
Relational reinforcement learning
Machine Learning - Special issue on inducive logic programming
Dynamic Programming and Optimal Control
Dynamic Programming and Optimal Control
Machine Learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Neuro-Dynamic Programming
Knowledge-Based Systems in Artificial Intelligence: 2 Case Studies
Knowledge-Based Systems in Artificial Intelligence: 2 Case Studies
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Handling Real Numbers in ILP: A Step Towards Better Behavioural Clones (Extended Abstract)
ECML '95 Proceedings of the 8th European Conference on Machine Learning
Least-Squares Methods in Reinforcement Learning for Control
SETN '02 Proceedings of the Second Hellenic Conference on AI: Methods and Applications of Artificial Intelligence
Greedy linear value-approximation for factored Markov decision processes
Eighteenth national conference on Artificial intelligence
Optimal implementation of conjunctive queries in relational data bases
STOC '77 Proceedings of the ninth annual ACM symposium on Theory of computing
Relative Value Function Approximation TITLE2:
Relative Value Function Approximation TITLE2:
Learning Generalized Policies from Planning Examples Using Concept Languages
Applied Intelligence
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Integrating Guidance into Relational Reinforcement Learning
Machine Learning
Exploiting first-order regression in inductive policy selection
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Automatic basis function construction for approximate dynamic programming and reinforcement learning
ICML '06 Proceedings of the 23rd international conference on Machine learning
Learning tetris using the noisy cross-entropy method
Neural Computation
Analyzing feature generation for value-function approximation
Proceedings of the 24th international conference on Machine learning
The Journal of Machine Learning Research
Non-parametric policy gradients: a unified treatment of propositional and relational domains
Proceedings of the 25th international conference on Machine learning
Proceedings of the 25th international conference on Machine learning
Practical solution techniques for first-order MDPs
Artificial Intelligence
Learning to improve both efficiency and quality of planning
IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2
The first probabilistic track of the international planning competition
Journal of Artificial Intelligence Research
Journal of Artificial Intelligence Research
FLUCAP: a heuristic search planner for first-order MDPs
Journal of Artificial Intelligence Research
Learning first-order definitions of functions
Journal of Artificial Intelligence Research
Learning first-order definitions of functions
Journal of Artificial Intelligence Research
The automatic inference of state invariants in TIM
Journal of Artificial Intelligence Research
An analysis of Laplacian methods for value function approximation in MDPs
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Max-norm projections for factored MDPs
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1
Symbolic dynamic programming for first-order MDPs
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1
Top-down induction of first-order logical decision trees
Artificial Intelligence
Inductive policy selection for first-order MDPs
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
Feature-Discovering approximate value iteration methods
SARA'05 Proceedings of the 6th international conference on Abstraction, Reformulation and Approximation
Stochastic enforced hill-climbing
Journal of Artificial Intelligence Research
Hi-index | 0.01 |
Domain-specific features are important in representing problem structure throughout machine learning and decision-theoretic planning. In planning, once state features are provided, domain-independent algorithms such as approximate value iteration can learn weighted combinations of those features that often perform well as heuristic estimates of state value (e.g., distance to the goal). Successful applications in real-world domains often require features crafted by human experts. Here, we propose automatic processes for learning useful domain-specific feature sets with little or no human intervention. Our methods select and add features that describe state-space regions of high inconsistency in the Bellman equation (statewise Bellman error) during approximate value iteration. Our method can be applied using any real-valued-feature hypothesis space and corresponding learning method for selecting features from training sets of state-value pairs. We evaluate the method with hypothesis spaces defined by both relational and propositional feature languages, using nine probabilistic planning domains. We show that approximate value iteration using a relational feature space performs at the state-of-the-art in domain-independent stochastic relational planning. Our method provides the first domain-independent approach that plays Tetris successfully (without human-engineered features).