arXiv (Cornell University) · 2018 · 10 citations · 15 references
ComputingComputer ScienceArtificial IntelligenceKnowledge RepresentationMachine LearningPolicy LearningReinforcement LearningAbductive InferenceAbductive ReasoningHierarchical Reinforcement LearningPrior Related KnowledgeReinforcementReinforcement Learning ModelsState-space Structure
One of the key challenges in applying reinforcement learning to real-life problems is that the amount of train-and-error required to learn a good policy increases drastically as the task becomes complex. One potential solution to this problem is to combine reinforcement learning with automated symbol planning and utilize prior knowledge on the domain. However, existing methods have limitations in their applicability and expressiveness. In this paper we propose a hierarchical reinforcement learning method based on abductive symbolic planning. The planner can deal with user-defined evaluation functions and is not based on the Herbrand theorem. Therefore it can utilize prior knowledge of the rewards and can work in a domain where the state space is unknown. We demonstrate empirically that our architecture significantly improves learning efficiency with respect to the amount of training examples on the evaluation domain, in which the state space is unknown and there exist multiple goals.
15
Matthew Richardson, Pedro Domingos · Machine Learning · 2006 · 2.7K citations · Full text
General Game Playing: Overview of the AAAI Competition
Michael Genesereth, Nathaniel Love, Barney Pell · 2005 · 543 citations
An abductive event calculus planner
Murray Shanahan · The Journal of Logic Programming · 2000 · 147 citations
Probabilistic semantics for cost based abduction
Eugene Charniak, Solomon Eyal Shimony · 1990 · 97 citations