Bayesian reinforcement learning: A survey
Bayesian methods for machine learning have been widely investigated, yielding principled
methods for incorporating prior information into inference algorithms. In this survey, we …
methods for incorporating prior information into inference algorithms. In this survey, we …
A survey of available corpora for building data-driven dialogue systems
During the past decade, several areas of speech and language understanding have
witnessed substantial breakthroughs from the use of data-driven models. In the area of …
witnessed substantial breakthroughs from the use of data-driven models. In the area of …
Sample-based bounds for coherent risk measures: Applications to policy synthesis and verification
Autonomous systems are increasingly used in highly variable and uncertain environments
giving rise to the pressing need to consider risk in both the synthesis and verification of …
giving rise to the pressing need to consider risk in both the synthesis and verification of …
Structured probabilistic modelling for dialogue management
P Lison - 2014 - duo.uio.no
This thesis presents a new modelling framework for dialogue management based on the
concept of probabilistic rules. Probabilistic rules are defined as if... then... else constructions …
concept of probabilistic rules. Probabilistic rules are defined as if... then... else constructions …
A comprehensive reinforcement learning framework for dialogue management optimization
L Daubigney, M Geist… - IEEE Journal of …, 2012 - ieeexplore.ieee.org
Reinforcement learning is now an acknowledged approach for optimizing the interaction
strategy of spoken dialogue systems. If the first considered algorithms were quite basic (like …
strategy of spoken dialogue systems. If the first considered algorithms were quite basic (like …
Knowledge-based hierarchical POMDPs for task planning
The main goal in task planning is to build a sequence of actions that takes an agent from an
initial state to a goal state. In robotics, this is particularly difficult because actions usually …
initial state to a goal state. In robotics, this is particularly difficult because actions usually …
Reinforcement learning for parameter estimation in statistical spoken dialogue systems
Reinforcement techniques have been successfully used to maximise the expected
cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used …
cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used …
The state-of-the-art in autonomous wheelchairs controlled through natural language: A survey
T Williams, M Scheutz - Robotics and Autonomous Systems, 2017 - Elsevier
Natural language is a flexible and powerful control modality which can transform a
wheelchair from a vehicle into a genuine helper. While autonomous wheelchairs are …
wheelchair from a vehicle into a genuine helper. While autonomous wheelchairs are …
Model-based bayesian reinforcement learning for dialogue management
P Lison - arXiv preprint arXiv:1304.1819, 2013 - arxiv.org
Reinforcement learning methods are increasingly used to optimise dialogue policies from
experience. Most current techniques are model-free: they directly estimate the utility of …
experience. Most current techniques are model-free: they directly estimate the utility of …
Maca: A modular architecture for conversational agents
HP Truong, P Parthasarathi… - Proceedings of the 18th …, 2017 - aclanthology.org
We propose a software architecture designed to ease the implementation of dialogue
systems. The Modular Architecture for Conversational Agents (MACA) uses a plug-n-play …
systems. The Modular Architecture for Conversational Agents (MACA) uses a plug-n-play …