Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning

07/19/2017
by   Stefan Ultes, et al.
0

Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e.g., the dialogue success and the dialogue length. In this work, we propose a structured method for finding a good balance between these components by searching for the optimal reward component weighting. To render this search feasible, we use multi-objective reinforcement learning to significantly reduce the number of training dialogues required. We apply our proposed method to find optimized component weights for six domains and compare them to a default baseline.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/01/2011

An Application of Reinforcement Learning to Dialogue Strategy Selection in a Spoken Dialogue System for Email

This paper describes a novel method by which a spoken dialogue system ca...
research
11/26/2016

Deep Reinforcement Learning for Multi-Domain Dialogue Systems

Standard deep reinforcement learning methods such as Deep Q-Networks (DQ...
research
05/24/2016

On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems

The ability to compute an accurate reward function is essential for opti...
research
04/01/2022

Automating Staged Rollout with Reinforcement Learning

Staged rollout is a strategy of incrementally releasing software updates...
research
05/17/2023

A proof of imitation of Wasserstein inverse reinforcement learning for multi-objective optimization

We prove Wasserstein inverse reinforcement learning enables the learner'...
research
03/31/2018

Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling

Recent statistical approaches have improved the robustness and scalabili...

Please sign up or login with your details

Forgot password? Click here to reset