2002 · 93 citations · 10 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningMarkov Decision ProcessesAction RepresentationPolicy IterationPolicy LearningReinforcement LearningReinforcement Learning FoundationsValue FunctionsPolicy RepresentationReinforcement Learning ModelsReinforcement Learning Theory
We present PolicyBlocks, an algorithm by which a reinforcement learning agent can extract useful macro-actions from a set of related tasks. The agent creates macroactions by finding commonalities in solutions to previous tasks. Using these macro-actions, learning to do future related tasks is accelerated.
10
Reinforcement Learning: An Introduction
IEEE Transactions on Neural Networks · 2005 · 25.8K citations
The theory of learning by doing.
Yuichiro Anzai, Herbert A. Simon · PubMed · 1979 · 609 citations