English
Related papers

Related papers: Adversarial Advantage Actor-Critic Model for Task-…

200 papers

To improve policy robustness of deep reinforcement learning agents, a line of recent works focus on producing disturbances of the environment. Existing approaches of the literature to generate meaningful disturbances of the environment are…

Machine Learning · Computer Science 2022-10-04 Lucas Schott , Hatem Hajri , Sylvain Lamprier

Large language models (LLMs) have demonstrated a remarkable ability to serve as general-purpose tools for various language-based tasks. Recent works have demonstrated that the efficacy of such models can be improved through iterative dialog…

Computation and Language · Computer Science 2025-03-07 Andrew Estornell , Jean-Francois Ton , Yuanshun Yao , Yang Liu

Conventional Reinforcement Learning (RL) algorithms, typically focused on estimating or maximizing expected returns, face challenges when refining offline pretrained models with online experiences. This paper introduces Generative Actor…

Machine Learning · Computer Science 2025-12-29 Aoyang Qin , Deqian Kong , Wei Wang , Ying Nian Wu , Song-Chun Zhu , Sirui Xie

We reformulate the option framework as two parallel augmented MDPs. Under this novel formulation, all policy optimization algorithms can be used off the shelf to learn intra-option policies, option termination conditions, and a master…

Machine Learning · Computer Science 2019-09-12 Shangtong Zhang , Shimon Whiteson

Communication lays the foundation for human cooperation. It is also crucial for multi-agent cooperation. However, existing work focuses on broadcast communication, which is not only impractical but also leads to information redundancy that…

Machine Learning · Computer Science 2021-04-30 Ziluo Ding , Tiejun Huang , Zongqing Lu

Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement…

Computation and Language · Computer Science 2020-04-24 Ryuichi Takanobu , Runze Liang , Minlie Huang

Actor-critic (AC) methods are ubiquitous in reinforcement learning. Although it is understood that AC methods are closely related to policy gradient (PG), their precise connection has not been fully characterized previously. In this paper,…

Artificial Intelligence · Computer Science 2021-06-15 Junfeng Wen , Saurabh Kumar , Ramki Gummadi , Dale Schuurmans

Deep reinforcement learning (RL) methods have significant potential for dialogue policy optimisation. However, they suffer from a poor performance in the early stages of learning. This is especially problematic for on-line learning with…

Computation and Language · Computer Science 2017-07-06 Pei-Hao Su , Pawel Budzianowski , Stefan Ultes , Milica Gasic , Steve Young

There is an increasing demand for task-oriented dialogue systems which can assist users in various activities such as booking tickets and restaurant reservations. In order to complete dialogues effectively, dialogue policy plays a key role…

Computation and Language · Computer Science 2019-09-23 Tian Lan , Xianling Mao , Heyan Huang

In reinforcement learning for partially observable environments, many successful algorithms have been developed within the asymmetric learning paradigm. This paradigm leverages additional state information available at training time for…

Machine Learning · Computer Science 2025-09-09 Gaspard Lambrechts , Damien Ernst , Aditya Mahajan

In this paper, we propose to use deep policy networks which are trained with an advantage actor-critic method for statistically optimised dialogue systems. First, we show that, on summary state and action spaces, deep Reinforcement Learning…

Computation and Language · Computer Science 2016-09-13 Mehdi Fatemi , Layla El Asri , Hannes Schulz , Jing He , Kaheer Suleman

Reinforcement Learning (RL) has been witnessed its potential for training a dialogue policy agent towards maximizing the accumulated rewards given from users. However, the reward can be very sparse for it is usually only provided at the end…

Computation and Language · Computer Science 2021-11-03 Hongru Wang , Huimin Wang , Zezhong Wang , Kam-Fai Wong

Both generative adversarial networks (GAN) in unsupervised learning and actor-critic methods in reinforcement learning (RL) have gained a reputation for being difficult to optimize. Practitioners in both fields have amassed a large number…

Machine Learning · Computer Science 2017-01-19 David Pfau , Oriol Vinyals

We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning. MAC is a policy gradient algorithm that uses the agent's explicit representation of all action values to estimate the gradient…

This paper proposes the Cooperative Soft Actor Critic (CSAC) method of enabling consecutive reinforcement learning agents to cooperatively solve a long time horizon multi-stage task. This method is achieved by modifying the policy of each…

Machine Learning · Computer Science 2020-07-02 Jordan Erskine , Chris Lehnert

As an important algorithm in deep reinforcement learning, advantage actor critic (A2C) has been widely succeeded in both discrete and continuous control tasks with raw pixel inputs, but its sample efficiency still needs to improve more. In…

Machine Learning · Computer Science 2022-02-15 Yuan Wang , Chunyuan Zhang , Tianzong Yu , Meng Ma

Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contrast successful actions against suboptimal alternatives and…

Artificial Intelligence · Computer Science 2026-03-10 Weize Liu , Minghui Liu , Sy-Tuyen Ho , Souradip Chakraborty , Xiyao Wang , Furong Huang

Reinforcement learning based dialogue policies are typically trained in interaction with a user simulator. To obtain an effective and robust policy, this simulator should generate user behaviour that is both realistic and varied. Current…

Computation and Language · Computer Science 2023-06-02 Simon Keizer , Caroline Dockes , Norbert Braunschweiler , Svetlana Stoyanchev , Rama Doddipatla

We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples. Our framework is motivated by actor-critic reinforcement learning, but can be applied to both reinforcement and supervised learning.…

Machine Learning · Computer Science 2017-06-30 Flood Sung , Li Zhang , Tao Xiang , Timothy Hospedales , Yongxin Yang

In this work, we propose Behavior-Guided Actor-Critic (BAC), an off-policy actor-critic deep RL algorithm. BAC mathematically formulates the behavior of the policy through autoencoders by providing an accurate estimation of how frequently…

Machine Learning · Computer Science 2021-04-12 Ammar Fayad , Majd Ibrahim