2009 · 42 citations · 7 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningMarkov Decision ProcessesComputational ModelingDialogue SystemsMonte Carlo MethodsMonte Carlo SimulationPartially Observable Markov Decision ProcessesReinforcement LearningBelief NetworksDialog SystemsGrid-based SamplingNearest Neighbor InterpolationSpoken Dialogue SystemsState-value FunctionUser SimulationValue Function Estimation
In real-world applications, modelling dialogue as a POMDP requires the use of a summary space for the dialogue state representation to ensure tractability. Sub-optimal estimation of the value function governing the selection of system responses can then be obtained using a grid-based approach on the belief space. In this work, the Monte-Carlo control technique is extended so as to reduce training over-fitting and to improve robustness to semantic noise in the user input. This technique uses a database of belief vector prototypes to choose the optimal system action. A locally weighted k-nearest neighbor scheme is introduced to smooth the decision process by interpolating the value function, resulting in higher user simulation performance.
7
Reinforcement Learning: An Introduction
IEEE Transactions on Neural Networks · 2005 · 25.8K citations
Christopher G. Atkeson, Andrew Moore, Stefan Schaal · Artificial Intelligence Review · 1997 · 1.7K citations
Agenda-based user simulation for bootstrapping a POMDP dialogue system
Jost Schatzmann, Blaise Thomson, Karl Weilhammer et al. · 2007 · 339 citations · Full text