Open AccessJournal Article
Journal of Artificial Intelligence Research: Preface
Reads0
Chats0
About:
This article is published in Journal of Artificial Intelligence Research.The article was published on 2001-01-01 and is currently open access. It has received 92 citations till now.read more
Citations
More filters
Proceedings ArticleDOI
SDD: a new canonical representation of propositional knowledge bases
TL;DR: A new representation of propositional knowledge bases, the Sentential Decision Diagram (SDD), which is interesting for a number of reasons, including that it is canonical in the presence of additional properties that resemble reduction rules of OBDDs.
Proceedings ArticleDOI
LTL and Beyond: Formal Languages for Reward Function Specification in Reinforcement Learning
Alberto Camacho,Rodrigo Toro Icarte,Toryn Q. Klassen,Richard Anthony Valenzano,Sheila A. McIlraith +4 more
TL;DR: This work proposes using reward machines (RMs), which are automata-based representations that expose reward function structure, as a normal form representation for reward functions, to ease the burden of complex reward function specification.
Proceedings Article
Interactive teaching strategies for agent training
TL;DR: Experimental results show that strategies for a teacher and a student to jointly identify advising opportunities so that the teacher is not required to constantly monitor the student reduce the amount of attention required from the teacher compared to teacher-initiated strategies, while maintaining similar learning gains.
Journal ArticleDOI
Backjumping for quantified Boolean logic satisfiability
TL;DR: This paper shows how it is possible to extend the conflict-directed backjumping schema for SAT to QBF: when applicable, it allows to jump over existentially quantified literals while backtracking, and introduces solution-directedBackjumping, which allows the same for universally quantified Literals.
Proceedings Article
Using task features for zero-shot knowledge transfer in lifelong learning
TL;DR: It is shown that using task descriptors improves the performance of the learned task policies, providing both theoretical justification for the benefit and empirical demonstration of the improvement across a variety of dynamical control problems.
References
More filters
Proceedings ArticleDOI
SDD: a new canonical representation of propositional knowledge bases
TL;DR: A new representation of propositional knowledge bases, the Sentential Decision Diagram (SDD), which is interesting for a number of reasons, including that it is canonical in the presence of additional properties that resemble reduction rules of OBDDs.
Proceedings ArticleDOI
LTL and Beyond: Formal Languages for Reward Function Specification in Reinforcement Learning
Alberto Camacho,Rodrigo Toro Icarte,Toryn Q. Klassen,Richard Anthony Valenzano,Sheila A. McIlraith +4 more
TL;DR: This work proposes using reward machines (RMs), which are automata-based representations that expose reward function structure, as a normal form representation for reward functions, to ease the burden of complex reward function specification.
Proceedings Article
Interactive teaching strategies for agent training
TL;DR: Experimental results show that strategies for a teacher and a student to jointly identify advising opportunities so that the teacher is not required to constantly monitor the student reduce the amount of attention required from the teacher compared to teacher-initiated strategies, while maintaining similar learning gains.
Journal ArticleDOI
Backjumping for quantified Boolean logic satisfiability
TL;DR: This paper shows how it is possible to extend the conflict-directed backjumping schema for SAT to QBF: when applicable, it allows to jump over existentially quantified literals while backtracking, and introduces solution-directedBackjumping, which allows the same for universally quantified Literals.
Journal ArticleDOI
Learning to Solve NP-Complete Problems: A Graph Neural Network for Decision TSP
TL;DR: In this paper, the authors show that GNNs can learn to solve the decision variant of the Traveling Salesperson Problem (TSP), a highly relevant NP-complete problem.