Reinforcement learning methods have been used to compute dialog policies from language-based interaction experiences. Efficiency is of particular importance in dialog policy learning, because of the considerable cost of interacting with people, and the very poor user experience from low-quality conversations. Aiming at improving the efficiency of dialog policy learning, we develop algorithm LHUA (Learning with Hindsight, User modeling, and Adaptation) that, for the first time, enables dialog agents to adaptively learn with hindsight from both simulated and real users. Simulation and hindsight provide the dialog agent with more experience and more (positive) reinforcements respectively. Experimental results suggest that, in success rate and policy quality, LHUA outperforms competitive baselines from the literature, including its no-simulation, no-adaptation, and no-hindsight counterparts.
University of Science and Technology of China（中国科学技术大学）；SUNY Binghamton（纽约州立大学宾汉姆顿分校）
Reinforcement learning methods have been used for learning dialogue policies. However, learning an effective dialogue policy frequently requires prohibitively many conversations. This is partly because of the sparse rewards in dialogues, and the very few successful dialogues in early learning phase. Hindsight experience replay (HER) enables learning from failures, but the vanilla HER is inapplicable to dialogue learning due to the implicit goals. In this work, we develop two complex HER methods providing different trade-offs between complexity and performance, and, for the first time, enabled …
Xi’an Jiaotong University（西安交通大学）；National University of Singapore（新加坡国立大学）
Reinforcement Learning(RL) with sparse rewards is a major challenge. We propose \emph{Hindsight Trust Region Policy Optimization}(HTRPO), a new RL algorithm that extends the highly successful TRPO algorithm with \emph{hindsight} to tackle the challenge of sparse rewards. Hindsight refers to the algorithm's ability to learn from information across goals, including ones not intended for the current task. HTRPO leverages two main ideas. It introduces QKL, a quadratic approximation to the KL divergence constraint on the trust region, leading to reduced variance in KL divergence estimation and impr…
A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behavior to unseen goals, such policies may also enable higher-level planning based on subgoals. In sparse-reward environments, the capacity to exploit information about the degree to which an arbitrary goal has been achieved while another goal was intended appears crucial to enable sample efficient learning. However, reinforcement learning agents have only recently been endowed with such capacity for hindsight. In this p…
Multi-task reinforcement learning (RL) aims to simultaneously learn policies for solving many tasks. Several prior works have found that relabeling past experience with different reward functions can improve sample efficiency. Relabeling methods typically ask: if, in hindsight, we assume that our experience was optimal for some task, for what task was it optimal? In this paper, we show that hindsight relabeling is inverse RL, an observation that suggests that we can use inverse RL in tandem for RL algorithms to efficiently solve many tasks. We use this idea to generalize goal-relabeling techni…
Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses. Existing MADP models usually imitate action combinations from the labeled multi-action dialog samples. Due to data limitations, they generalize poorly toward unseen dialog flows. While interactive learning and reinforcement learning algorithms can be applied to incorporate external data sources of real users and user simulators, they take significant manual effort to build and suffer from instab…
Designing optimal reward functions has been desired but extremely difficult in reinforcement learning (RL). When it comes to modern complex tasks, sophisticated reward functions are widely used to simplify policy learning yet even a tiny adjustment on them is expensive to evaluate due to the drastically increasing cost of training. To this end, we propose a hindsight reward tweaking approach by designing a novel paradigm for deep reinforcement learning to model the influences of reward functions within a near-optimal space. We simply extend the input observation with a condition vector linearl…
School of software engineering, South China University of Technology（华南理工大学软件学院）
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 train on, have been considered as an affordable substitute for real users. However, this random sampling method ignores the law of human learning, making the learned dialogue policy inefficient and unstable. We propose a novel framework, Automatic Curriculum Learning-based Deep Q-Network (ACL-DQN), which replaces the traditional random sampling method with a tea…
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 of a dialog session, which causes unaffordable interaction requirements for an acceptable dialog agent. Distinguished from many efforts dedicated to optimizing the policy and recovering the reward alternatively which suffers from easily getting stuck in local optima and model collapse, we decompose the adversarial training into two steps: 1) we integrate a …
Reinforcement learning (RL) is an effective approach to learn an optimal dialog policy for task-oriented visual dialog systems. A common practice is to apply RL on a neural sequence-to-sequence (seq2seq) framework with the action space being the output vocabulary in the decoder. However, it is difficult to design a reward function that can achieve a balance between learning an effective policy and generating a natural dialog response. This paper proposes a novel framework that alternatively trains a RL policy for image guessing and a supervised seq2seq model to improve dialog generation qualit…
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；Cambricon Technologies（寒武纪科技）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology of China（中国科学技术大学）
Policy gradient methods are appealing in deep reinforcement learning but suffer from high variance of gradient estimate. To reduce the variance, the state value function is applied commonly. However, the effect of the state value function becomes limited in stochastic dynamic environments, where the unexpected state dynamics and rewards will increase the variance. In this paper, we propose to replace the state value function with a novel hindsight value function, which leverages the information from the future to reduce the variance of the gradient estimate for stochastic dynamic environments.…
Learning a goal-oriented dialog policy is generally performed offline with supervised learning algorithms or online with reinforcement learning (RL). Additionally, as companies accumulate massive quantities of dialog transcripts between customers and trained human agents, encoder-decoder methods have gained popularity as agent utterances can be directly treated as supervision without the need for utterance-level annotations. However, one potential drawback of such approaches is that they myopically generate the next agent utterance without regard for dialog-level considerations. To resolve thi…
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 (RL) outperforms Gaussian Processes methods. Summary state and action spaces lead to good performance but require pre-engineering effort, RL knowledge, and domain expertise. In order to remove the need to define such summary spaces, we show that deep RL can also be trained efficiently on the original state and action spaces. Dialogue systems based on partia…
Episodic self-imitation learning, a novel self-imitation algorithm with a trajectory selection module and an adaptive loss function, is proposed to speed up reinforcement learning. Compared to the original self-imitation learning algorithm, which samples good state-action pairs from the experience replay buffer, our agent leverages entire episodes with hindsight to aid self-imitation learning. A selection module is introduced to filter uninformative samples from each episode of the update. The proposed method overcomes the limitations of the standard self-imitation learning algorithm, a transi…
Korea University（高丽大学）；Massachusetts Institute of Technology（麻省理工学院）
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 generator and reward estimator. During optimization, the reward estimator often overwhelms the policy generator and produces excessively uninformative gradients. We proposes the Variational Reward estimator Bottleneck (VRB), which is an effective regularization method that aims to constrain unproductive information flows between inputs and the reward estimator. T…
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shanghai AI Laboratory（上海人工智能实验室）；University of Science and Technology of China（中国科学技术大学）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）
Human conversation is inherently complex, often spanning many different topics/domains. This makes policy learning for dialogue systems very challenging. Standard flat reinforcement learning methods do not provide an efficient framework for modelling such dialogues. In this paper, we focus on the under-explored problem of multi-domain dialogue management. First, we propose a new method for hierarchical reinforcement learning using the option framework. Next, we show that the proposed architecture learns faster and arrives at a better policy than the existing flat ones do. Moreover, we show how…
UniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement Learning
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Peking University（北京大学）；Mininglamp Technology（明略科技）；Key Laboratory of Computing Power Network and Information Security, Ministry of Education（计算力网络与信息安全教育部重点实验室；山东省计算中心（齐鲁工业大学（山东省科学院）））；Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences)（计算力互联网与服务计算重点实验室，山东省计算机科学基础研究中心）；Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science
Tsinghua University（清华大学）；Tencent AI Lab（腾讯人工智能实验室）
Multi-goal reinforcement learning is widely applied in planning and robot manipulation. Two main challenges in multi-goal reinforcement learning are sparse rewards and sample inefficiency. Hindsight Experience Replay (HER) aims to tackle the two challenges via goal relabeling. However, HER-related works still need millions of samples and a huge computation. In this paper, we propose Multi-step Hindsight Experience Replay (MHER), incorporating multi-step relabeled returns based on $n$-step relabeling to improve sample efficiency. Despite the advantages of $n$-step relabeling, we theoretically a…
The recent success of reinforcement learning's (RL) in solving complex tasks is most often attributed to its capacity to explore and exploit an environment where it has been trained. Sample efficiency is usually not an issue since cheap simulators are available to sample data on-policy. On the other hand, task oriented dialogues are usually learnt from offline data collected using human demonstrations. Collecting diverse demonstrations and annotating them is expensive. Unfortunately, use of RL methods trained on off-policy data are prone to issues of bias and generalization, which are further …
Microsoft Research（微软研究院）；The Chinese University of Hong Kong（香港中文大学）
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 there leaves enough time for commute between arrival and hotel check-in. This paper addresses this challenge by formulating the task in the mathematical framework of options over Markov Decision Processes (MDPs), and proposing a hierarchical deep reinforcement learning approach to learning a dialogue manager that operates at different temporal scales. The d…
Microsoft Research（微软研究院）；Columbia University（哥伦比亚大学）；Google Inc.（谷歌公司）
Developing agents to engage in complex goal-oriented dialogues is challenging partly because the main learning signals are very sparse in long conversations. In this paper, we propose a divide-and-conquer approach that discovers and exploits the hidden structure of the task to enable efficient policy learning. First, given successful example dialogues, we propose the Subgoal Discovery Network (SDN) to divide a complex goal-oriented task into a set of simpler subgoals in an unsupervised fashion. We then use these subgoals to learn a multi-level policy by hierarchical reinforcement learning. We …
A learning dialogue agent can infer its behaviour from interactions with the users. These interactions can be taken from either human-to-human or human-machine conversations. However, human interactions are scarce and costly, making learning from few interactions essential. One solution to speedup the learning process is to guide the agent's exploration with the help of an expert. We present in this paper several imitation learning strategies for dialogue policy where the guiding expert is a near-optimal handcrafted policy. We incorporate these strategies with state-of-the-art reinforcement le…
Ludwig Maximilian University（路德维希-马克西米利安大学）；Siemens AG（西门子股份公司）
This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples. However, the collection of the required data in form of conversations between chat-bots and human agents is time-consuming and expensive. To mitigate this problem, we describe an efficient policy gradient method using positive memory retention, which significantly increases the sample-efficiency. We show that our method is 10 times more sample-efficient than policy gradients i…
Imperial College London（帝国理工学院）；Laiye Network Technology Co. Ltd.（来也网络科技有限公司）；KAIST（韩国科学技术院）；University of Bath（巴斯大学）
Designing task-oriented dialogue systems is a challenging research topic, since it needs not only to generate utterances fulfilling user requests but also to guarantee the comprehensibility. Many previous works trained end-to-end (E2E) models with supervised learning (SL), however, the bias in annotated system utterances remains as a bottleneck. Reinforcement learning (RL) deals with the problem through using non-differentiable evaluation metrics (e.g., the success rate) as rewards. Nonetheless, existing works with RL showed that the comprehensibility of generated system utterances could be co…
Listening to the Echo: User-Reaction Aware Policy Optimization via Scalar-Verbal Hybrid Reinforcement Learning
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
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 task success for modelling the reward signal, we use a reward based on user satisfaction estimation. We propose a novel estimator and show that it outperforms all previous estimators while learning temporal dependencies implicitly. Furthermore, we apply this novel user satisfaction estimation model live in simulated experiments where the satisfaction estimation…
University of Amsterdam（阿姆斯特丹大学）；Amazon（亚马逊）；Microsoft Research（微软研究院）
Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a dialogue finishes. Besides, the reward signal is manually designed by human experts, which requires domain knowledge. Recently, a number of adversarial learning methods have been proposed to learn the reward function together with the dialogue policy. However, to alternatively update the dialogue policy and the reward model on the fly, we are limited to policy-…
Microsoft Research（微软研究院）；The Chinese University of Hong Kong（香港中文大学）；National Taiwan University（台湾大学）
Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative is to use a user simulator. However, a user simulator usually lacks the language complexity of human interlocutors and the biases in its design may tend to degrade the agent. To address these issues, we present Deep Dyna-Q, which to our knowledge is the first deep RL framework that integrates planning for task-completion dialogue policy learning. We incorporate into the dialogue agent a model of the environment, referred to as the wor…
HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院航空航天信息研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tencent Hunyuan（腾讯文脉）；School of Computer Science and Technology, Tianjin University（天津大学计算机科学与技术学院）
Tencent AI Lab（腾讯人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）
In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem. In this paper, to enhance the diversity of relabeled goals, we develop FGI (Foresight Goal Inference), a new relabeling strategy that relabels the goals by looking into the future with a learned dynamics model. Besides, to improve sample efficiency, we propose to use the dynamics model to generate simulated trajectories for policy training. By integrating these two improvements, we introduce the MapGo framework (Model-…
One of the key reasons for the high sample complexity in reinforcement learning (RL) is the inability to transfer knowledge from one task to another. In standard multi-task RL settings, low-reward data collected while trying to solve one task provides little to no signal for solving that particular task and is hence effectively wasted. However, we argue that this data, which is uninformative for one task, is likely a rich source of information for other tasks. To leverage this insight and efficiently reuse data, we present Generalized Hindsight: an approximate inverse reinforcement learning te…
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering. It can be combined with an arbitrary off-policy RL algorithm and may be seen as a form of implicit curriculum. We demonstrate our approach on the task of manipulating objects with a robotic arm. In particular, we run experiments on three different tasks: pushing, sliding, and pick-and-place, in ea…
Georgia Institute of Technology（佐治亚理工学院）；Google Brain（谷歌大脑）；Google Cloud AI（谷歌云人工智能）
Reliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interaction, which is usually not affordable for large-scale experiments. Though researchers have attempted to use metrics (e.g., perplexity, BLEU) in language generation tasks or some model-based reinforcement learning methods (e.g., self-play evaluation) for automatic evaluation, these methods only show a very weak correlation with the actual human evaluation in practice. To bridge s…
Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences（中国科学院合肥物质科学研究院智能机械研究所）；University of Science and Technology of China（中国科学技术大学）
Exploration with sparse rewards remains a challenging research problem in reinforcement learning (RL). Especially for sequential object manipulation tasks, the RL agent always receives negative rewards until completing all sub-tasks, which results in low exploration efficiency. To solve these tasks efficiently, we propose a novel self-guided continual RL framework, RelayHER (RHER). RHER first decomposes a sequential task into new sub-tasks with increasing complexity and ensures that the simplest sub-task can be learned quickly by utilizing Hindsight Experience Replay (HER). Secondly, we design…
Cambridge University Engineering Department（剑桥大学工程系）
User Simulators are one of the major tools that enable offline training of task-oriented dialogue systems. For this task the Agenda-Based User Simulator (ABUS) is often used. The ABUS is based on hand-crafted rules and its output is in semantic form. Issues arise from both properties such as limited diversity and the inability to interface a text-level belief tracker. This paper introduces the Neural User Simulator (NUS) whose behaviour is learned from a corpus and which generates natural language, hence needing a less labelled dataset than simulators generating a semantic output. In compariso…
Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）
Automatic optimization of spoken dialog management policies that are robust to environmental noise has long been the goal for both academia and industry. Approaches based on reinforcement learning have been proved to be effective. However, the numerical representation of dialog policy is human-incomprehensible and difficult for dialog system designers to verify or modify, which limits its practical application. In this paper we propose a novel framework for optimizing dialog policies specified in domain language using genetic algorithm. The human-interpretable representation of policy makes th…
Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL). For RL, a policy gradient approach is natural, but is sample inefficient. In this paper, we present 3 methods for reducing the number of dialogs required to optimize an RNN-based dialog policy with RL. The key idea is to maintain a second RNN which predicts the value of the current policy, and to apply experience replay to both networks. On two tasks, t…
Sidi Mohamed Ben Abdallah University（西迪·穆罕默德·本·阿卜杜拉大学）
Nowadays, the current neural network models of dialogue generation(chatbots) show great promise for generating answers for chatty agents. But they are short-sighted in that they predict utterances one at a time while disregarding their impact on future outcomes. Modelling a dialogue's future direction is critical for generating coherent, interesting dialogues, a need that has led traditional NLP dialogue models that rely on reinforcement learning. In this article, we explain how to combine these objectives by using deep reinforcement learning to predict future rewards in chatbot dialogue. The …
Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling
South China University of Technology（华南理工大学）；Tsinghua University（清华大学）；The Hong Kong University of Science and Technology（香港科技大学）；Huawei 2012 Laboratories（华为2012实验室）；Shenzhen Technology University（深圳技术大学）
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Reinforcement learning has shown great potential in solving complex tasks when large amounts of data can be generated with little effort. In robotics, one approach to generate training data builds on simulations based on dynamics models derived from first principles. However, for tasks that, for instance, involve complex soft robots, devising such models is substantially more challenging. Being able to train effectively in increasingly complicated scenarios with reinforcement learning enables to take advantage of complex systems such as soft robots. Here, we leverage the imbalance in complexit…
Ludwig Maximilian University（路德维希-马克西米利安大学）；Siemens AG（西门子股份公司）
Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extensions for policy gradient methods, which are referred to as Tempered Policy Gradients (TPGs). On a recent AI-testbed, i.e., the GuessWhat?! game, we achieve significant improvements with two innovations. The first one is an extension of the state-of-the-art solutions with Seq2Seq and…
Tsinghua University（清华大学）；Tencent Robotics X（腾讯机器人X实验室）；Eindhoven University of Technology（埃因霍温理工大学）；King’s College London（伦敦国王学院）
Solving multi-goal reinforcement learning (RL) problems with sparse rewards is generally challenging. Existing approaches have utilized goal relabeling on collected experiences to alleviate issues raised from sparse rewards. However, these methods are still limited in efficiency and cannot make full use of experiences. In this paper, we propose Model-based Hindsight Experience Replay (MHER), which exploits experiences more efficiently by leveraging environmental dynamics to generate virtual achieved goals. Replacing original goals with virtual goals generated from interaction with a trained dy…
This paper presents a model for end-to-end learning of task-oriented dialog systems. The main component of the model is a recurrent neural network (an LSTM), which maps from raw dialog history directly to a distribution over system actions. The LSTM automatically infers a representation of dialog history, which relieves the system developer of much of the manual feature engineering of dialog state. In addition, the developer can provide software that expresses business rules and provides access to programmatic APIs, enabling the LSTM to take actions in the real world on behalf of the user. The…
University of Cambridge（剑桥大学）；DeepMind Technologies（深度思维科技）
In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans. A part of this effort is the policy optimisation task, which attempts to find a policy describing how to respond to humans, in the form of a function taking the current state of the dialogue and returning the response of the system. In this paper, we investigate deep reinforcement learning approaches to solve this problem. Particular attention is given to actor-critic methods, off-policy reinforcement learning with experience replay, and various methods aimed a…
Adaptable Hindsight Experience Replay for Search-Based Learning
Technical University of Darmstadt（德累斯顿技术大学）；Hessian Center for Artificial Intelligence（黑森人工智能中心）；German Research Center for Artificial Intelligence（德国人工智能研究中心）；Centre for Cognitive Science（认知科学中心）；National Research Center for Applied Cybersecurity ATHENE（应用网络安全国家研究中心ATHENE）
本文提出 Adaptable HER 框架，将事后经验回放与 AlphaZero 式搜索学习灵活集成，通过可调整的重新标记目标、策略目标和轨迹选择，在稀疏奖励及方程发现等任务中超越纯监督学习和强化学习。
