Applications of circumscription to formalizing common-sense knowledge
Artificial Intelligence
Readings in nonmonotonic reasoning
Readings in nonmonotonic reasoning
ADL: exploring the middle ground between STRIPS and the situation calculus
Proceedings of the first international conference on Principles of knowledge representation and reasoning
Artificial intelligence and mathematical theory of computation
On the complexity of propositional knowledge base revision, updates, and counterfactuals
Artificial Intelligence
Factorial Hidden Markov Models
Machine Learning - Special issue on learning with probabilistic representations
Planning and acting in partially observable stochastic domains
Artificial Intelligence
A new method for consequence finding and compilation in restricted languages
AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
A Computing Procedure for Quantification Theory
Journal of the ACM (JACM)
Bucket elimination: a unifying framework for reasoning
Artificial Intelligence
Model checking
Approximate learning of dynamic models
Proceedings of the 1998 conference on Advances in neural information processing systems II
Chaff: engineering an efficient SAT solver
Proceedings of the 38th annual Design Automation Conference
Symbolic Logic and Mechanical Theorem Proving
Symbolic Logic and Mechanical Theorem Proving
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Neuro-Dynamic Programming
On the semantics of updates in databases
PODS '83 Proceedings of the 2nd ACM SIGACT-SIGMOD symposium on Principles of database systems
Computing Circumscription Revisited: A Reduction Algorithm
Journal of Automated Reasoning
Minimal Answer Computation and SOL
JELIA '02 Proceedings of the European Conference on Logics in Artificial Intelligence
Exploring artificial intelligence in the new millennium
A completeness theorem and a computer program for finding theorems derivable from given axioms
A completeness theorem and a computer program for finding theorems derivable from given axioms
Algorithms for sequential decision-making
Algorithms for sequential decision-making
Dynamic bayesian networks: representation, inference and learning
Dynamic bayesian networks: representation, inference and learning
Learning and discovery of predictive state representations in dynamical systems with reset
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Looping suffix tree-based inference of partially observable hidden state
ICML '06 Proceedings of the 23rd international conference on Machine learning
ARMS: an automatic knowledge engineering tool for learning action models for AI planning
The Knowledge Engineering Review
Reasoning about partially observed actions
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Learning partially observable action schemas
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Learning partially observable action models: efficient algorithms
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Stochastic filtering in a probabilistic action model
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
Journal of Artificial Intelligence Research
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1
Theorem proving with structured theories
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
Reinforcement learning in POMDPs without resets
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Learning partially observable deterministic action models
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Searching for planning operators with context-dependent and probabilistic effects
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
Discovering the hidden structure of complex dynamic systems
UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Learning finite-state controllers for partially observable environments
UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Learning the structure of dynamic probabilistic networks
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
Deterministic POMDPs revisited
UAI '09 Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence
Learning action effects in partially observable domains
Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
Artificial Intelligence
Heuristic rule induction for decision making in near-deterministic domains
SETN'10 Proceedings of the 6th Hellenic conference on Artificial Intelligence: theories, models and applications
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Learning and reasoning with action-related places for robust mobile manipulation
Journal of Artificial Intelligence Research
On estimating actuation delays in elastic computing systems
Proceedings of the 8th International Symposium on Software Engineering for Adaptive and Self-Managing Systems
Hi-index | 0.00 |
We present exact algorithms for identifying deterministic-actions' effects and preconditions in dynamic partially observable domains. They apply when one does not know the action model (the way actions affect the world) of a domain and must learn it from partial observations over time. Such scenarios are common in real world applications. They are challenging for AI tasks because traditional domain structures that underly tractability (e.g., conditional independence) fail there (e.g., world features become correlated). Our work departs from traditional assumptions about partial observations and action models. In particular, it focuses on problems in which actions are deterministic of simple logical structure and observation models have all features observed with some frequency. We yield tractable algorithms for the modified problem for such domains. Our algorithms take sequences of partial observations over time as input, and output deterministic action models that could have lead to those observations. The algorithms output all or one of those models (depending on our choice), and are exact in that no model is misclassified given the observations. Our algorithms take polynomial time in the number of time steps and state features for some traditional action classes examined in the AI-planning literature, e.g., STRIPS actions. In contrast, traditional approaches for HMMs and Reinforcement Learning are inexact and exponentially intractable for such domains. Our experiments verify the theoretical tractability guarantees, and show that we identify action models exactly. Several applications in planning, autonomous exploration, and adventure-game playing already use these results. They are also promising for probabilistic settings, partially observable reinforcement learning, and diagnosis.