English
Related papers

Related papers: Anti-Overestimation Dialogue Policy Learning for T…

200 papers

Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches for optimal perturbation policies via a controller trained using performance rewards of a sampled policy on the target task, hence reducing data-level model bias. While…

Computation and Language · Computer Science 2019-10-01 Tong Niu , Mohit Bansal

Dialogue policy learning based on reinforcement learning is difficult to be applied to real users to train dialogue agents from scratch because of the high cost. User simulators, which choose random user goals for the dialogue agent to…

Computation and Language · Computer Science 2020-12-29 Yangyang Zhao , Zhenyu Wang , Zhenhua Huang

In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm…

Machine Learning · Computer Science 2011-09-09 Mohammad Gheshlaghi Azar , Vicenc Gomez , Hilbert J. Kappen

To overcome the curse of dimensionality and curse of modeling in Dynamic Programming (DP) methods for solving classical Markov Decision Process (MDP) problems, Reinforcement Learning (RL) algorithms are popular. In this paper, we consider…

Machine Learning · Computer Science 2018-11-29 Arghyadip Roy , Vivek Borkar , Abhay Karandikar , Prasanna Chaporkar

We propose a fully distributed actor-critic algorithm approximated by deep neural networks, named \textit{Diff-DAC}, with application to single-task and to average multitask reinforcement learning (MRL). Each agent has access to data from…

Trainable chatbots that exhibit fluent and human-like conversations remain a big challenge in artificial intelligence. Deep Reinforcement Learning (DRL) is promising for addressing this challenge, but its successful application remains an…

The task-oriented spoken dialogue system (SDS) aims to assist a human user in accomplishing a specific task (e.g., hotel booking). The dialogue management is a core part of SDS. There are two main missions in dialogue management: dialogue…

Computation and Language · Computer Science 2020-09-23 Zhi Chen , Lu Chen , Xiaoyuan Liu , Kai Yu

Early stopping based on the validation set performance is a popular approach to find the right balance between under- and overfitting in the context of supervised learning. However, in reinforcement learning, even for supervised…

Machine Learning · Computer Science 2023-03-20 Nicolai Dorka , Tim Welschehold , Wolfram Burgard

Improving data utilization efficiency is critical for scaling reinforcement learning (RL) for long-horizon tasks where generating trajectories is expensive. However, the dominant RL methods for LLMs are largely on-policy: they update each…

Despite its notable success in adversarial learning approaches to multi-domain task-oriented dialog system, training the dialog policy via adversarial inverse reinforcement learning often fails to balance the performance of the policy…

Artificial Intelligence · Computer Science 2020-06-02 Jeiyoon Park , Chanhee Lee , Kuekyeng Kim , Heuiseok Lim

In value-based reinforcement learning (RL), unlike in supervised learning, the agent faces not a single, stationary, approximation problem, but a sequence of value prediction problems. Each time the policy improves, the nature of the…

Machine Learning · Computer Science 2021-01-05 Will Dabney , André Barreto , Mark Rowland , Robert Dadashi , John Quan , Marc G. Bellemare , David Silver

A major bottleneck for building statistical spoken dialogue systems for new domains and applications is the need for large amounts of training data. To address this problem, we adopt the multi-dimensional approach to dialogue management and…

Computation and Language · Computer Science 2022-04-15 Simon Keizer , Norbert Braunschweiler , Svetlana Stoyanchev , Rama Doddipatla

Learning suitable and well-performing dialogue behaviour in statistical spoken dialogue systems has been in the focus of research for many years. While most work which is based on reinforcement learning employs an objective measure like…

Computation and Language · Computer Science 2020-01-22 Stefan Ultes

Building a dialogue agent to fulfill complex tasks, such as travel planning, is challenging because the agent has to learn to collectively complete multiple subtasks. For example, the agent needs to reserve a hotel and book a flight so that…

Computation and Language · Computer Science 2017-07-25 Baolin Peng , Xiujun Li , Lihong Li , Jianfeng Gao , Asli Celikyilmaz , Sungjin Lee , Kam-Fai Wong

Reinforcement Learning (RL) has emerged as a transformative approach for aligning and enhancing Large Language Models (LLMs), addressing critical challenges in instruction following, ethical alignment, and reasoning capabilities. This…

Artificial Intelligence · Computer Science 2025-07-08 Saksham Sahai Srivastava , Vaneet Aggarwal

In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback…

Computation and Language · Computer Science 2018-04-19 Bing Liu , Gokhan Tur , Dilek Hakkani-Tur , Pararth Shah , Larry Heck

This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are considered:…

Machine Learning · Computer Science 2021-04-21 Tianyi Chen , Kaiqing Zhang , Georgios B. Giannakis , Tamer Başar

Value-based deep Reinforcement Learning (RL) algorithms suffer from the estimation bias primarily caused by function approximation and temporal difference (TD) learning. This problem induces faulty state-action value estimates and therefore…

Machine Learning · Computer Science 2021-11-15 Dogan C. Cicek , Enes Duran , Baturay Saglam , Kagan Kaya , Furkan B. Mutlu , Suleyman S. Kozat

Offline reinforcement learning (RL) is a challenging setting where existing off-policy actor-critic methods perform poorly due to the overestimation of out-of-distribution state-action pairs. Thus, various additional augmentations are…

Machine Learning · Computer Science 2023-02-23 Zifeng Zhuang , Kun Lei , Jinxin Liu , Donglin Wang , Yilang Guo

The Dynamic Task Assignment Problem (DTAP) concerns matching resources to tasks in real time while minimizing some objectives, like resource costs or task cycle time. In this work, we consider a DTAP variant where every task is a case…

Artificial Intelligence · Computer Science 2025-04-29 Riccardo Lo Bianco , Willem van Jaarsveld , Jeroen Middelhuis , Luca Begnardi , Remco Dijkman