Path-based relational reasoning over knowledge graphs has become increasingly popular due to a variety of downstream applications such as question answering in dialogue systems, fact prediction, and recommender systems. In recent years, reinforcement learning (RL) has provided solutions that are more interpretable and explainable than other deep learning models. However, these solutions still face several challenges, including large action space for the RL agent and accurate representation of entity neighborhood structure. We address these problems by introducing a type-enhanced RL agent that uses the local neighborhood information for efficient path-based reasoning over knowledge graphs. Our solution uses graph neural network (GNN) for encoding the neighborhood information and utilizes entity types to prune the action space. Experiments on real-world dataset show that our method outperforms state-of-the-art RL methods and discovers more novel paths during the training procedure.
Relational Reinforcement Learning (RRL) can offers various desirable features. Most importantly, it allows for incorporating expert knowledge into the learning, and hence leading to much faster learning and better generalization compared to the standard deep reinforcement learning. However, most of the existing RRL approaches are either incapable of incorporating expert background knowledge (e.g., in the form of explicit predicate language) or are not able to learn directly from non-relational data such as image. In this paper, we propose a novel deep RRL based on a differentiable Inductive Lo…
In this article, we extend the conventional framework of convolutional-Restricted-Boltzmann-Machine to learn highly abstract features among abitrary number of time related input maps by constructing a layer of multiplicative units, which capture the relations among inputs. In many cases, more than two maps are strongly related, so it is wise to make multiplicative unit learn relations among more input maps, in other words, to find the optimal relational-order of each unit. In order to enable our machine to learn relational order, we developed a reinforcement-learning method whose optimality is…
We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning. It uses self-attention to iteratively reason about the relations between entities in a scene and to guide a model-free policy. Our results show that in a novel navigation and planning task called Box-World, our agent finds interpretable solutions that improve upon baselines in terms of sample complexity, ability to generalize to more complex scenes than experienced during…
Although reinforcement learning has been successfully applied in many domains in recent years, we still lack agents that can systematically generalize. While relational inductive biases that fit a task can improve generalization of RL agents, these biases are commonly hard-coded directly in the agent's neural architecture. In this work, we show that we can incorporate relational inductive biases, encoded in the form of relational graphs, into agents. Based on this insight, we propose Grid-to-Graph (GTG), a mapping from grid structures to relational graphs that carry useful spatial relational i…
Various data mining tasks have been proposed to study Community Question Answering (CQA) platforms like Stack Overflow. The relatedness between some of these tasks provides useful learning signals to each other via Multi-Task Learning (MTL). However, due to the high heterogeneity of these tasks, few existing works manage to jointly solve them in a unified framework. To tackle this challenge, we develop a multi-relational graph based MTL model called Heterogeneous Multi-Task Graph Isomorphism Network (HMTGIN) which efficiently solves heterogeneous CQA tasks. In each training forward pass, HMTGI…
Distant supervision (DS) aims to generate large-scale heuristic labeling corpus, which is widely used for neural relation extraction currently. However, it heavily suffers from noisy labeling and long-tail distributions problem. Many advanced approaches usually separately address two problems, which ignore their mutual interactions. In this paper, we propose a novel framework named RH-Net, which utilizes Reinforcement learning and Hierarchical relational searching module to improve relation extraction. We leverage reinforcement learning to instruct the model to select high-quality instances. W…
School of Computing and Augmented Intelligence（计算与增强智能学院）；Arizona State University（亚利桑那州立大学）
Reinforcement learning in problems with symbolic state spaces is challenging due to the need for reasoning over long horizons. This paper presents a new approach that utilizes relational abstractions in conjunction with deep learning to learn a generalizable Q-function for such problems. The learned Q-function can be efficiently transferred to related problems that have different object names and object quantities, and thus, entirely different state spaces. We show that the learned generalized Q-function can be utilized for zero-shot transfer to related problems without an explicit, hand-coded…
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）
We address the problem of efficient exploration for transition model learning in the relational model-based reinforcement learning setting without extrinsic goals or rewards. Inspired by human curiosity, we propose goal-literal babbling (GLIB), a simple and general method for exploration in such problems. GLIB samples relational conjunctive goals that can be understood as specific, targeted effects that the agent would like to achieve in the world, and plans to achieve these goals using the transition model being learned. We provide theoretical guarantees showing that exploration with GLIB wil…
Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks and Autoregressive Policy Decomposition
Czech Technical University in Prague（布拉格捷克技术大学）；Artificial Intelligence Center, Department of Computer Science, Faculty of Electrical Engineering（电气工程学院计算机科学系人工智能中心）
In a robot-centered smart home, the robot observes the home states with its own sensors, and then it can change certain object states according to an operator's commands for remote operations, or imitate the operator's behaviors in the house for autonomous operations. To model the robot's imitation of the operator's behaviors in a dynamic indoor environment, we use multi-relational chains to describe the changes of environment states, and apply inverse reinforcement learning to encoding the operator's behaviors with a learned reward function. We implement this approach with a mobile robot, and…
Relational Multi-Agent Reinforcement Learning for Dynamic Pricing in High-Speed Railway Markets
Department of Technologies and Information Systems, Universidad de Castilla-La Mancha（卡斯蒂利亚-拉曼恰大学技术与信息系统系）；Warwick Manufacturing Group, University of Warwick（华威大学华威制造集团）
In this paper we explore previously unidentified connections between relational event model (REM) from the field of network science and inverse reinforcement learning (IRL) from the field of machine learning with respect to their ability to characterize sequences of directed social interaction events in group settings. REM is a conventional approach to tackle such a problem whereas the application of IRL is a largely unbeaten path. We begin by examining the mathematical components of both REM and IRL and find straightforward analogies between the two methods as well as unique characteristics o…
State-of-the-art reinforcement learning algorithms predominantly learn a policy from either a numerical state vector or images. Both approaches generally do not take structural knowledge of the task into account, which is especially prevalent in robotic applications and can benefit learning if exploited. This work introduces a neural network architecture that combines relational inductive bias and visual feedback to learn an efficient position control policy for robotic manipulation. We derive a graph representation that models the physical structure of the manipulator and combines the robot's…
Massachusetts Institute of Technology（麻省理工学院）；University of California Berkeley（加州大学伯克利分校）
Learning robotic manipulation tasks using reinforcement learning with sparse rewards is currently impractical due to the outrageous data requirements. Many practical tasks require manipulation of multiple objects, and the complexity of such tasks increases with the number of objects. Learning from a curriculum of increasingly complex tasks appears to be a natural solution, but unfortunately, does not work for many scenarios. We hypothesize that the inability of the state-of-the-art algorithms to effectively utilize a task curriculum stems from the absence of inductive biases for transferring k…
The University of Sydney（悉尼大学）；The University of Melbourne（墨尔本大学）；JD Explore Academy（京东探索研究院）
The generalization of model-based reinforcement learning (MBRL) methods to environments with unseen transition dynamics is an important yet challenging problem. Existing methods try to extract environment-specified information $Z$ from past transition segments to make the dynamics prediction model generalizable to different dynamics. However, because environments are not labelled, the extracted information inevitably contains redundant information unrelated to the dynamics in transition segments and thus fails to maintain a crucial property of $Z$: $Z$ should be similar in the same environment…
KU Leuven（鲁汶大学）；Université libre de Bruxelles（布鲁塞尔自由大学）；Örebro University（厄勒布鲁大学）
Probabilistic model checking has been developed for verifying systems that have stochastic and nondeterministic behavior. Given a probabilistic system, a probabilistic model checker takes a property and checks whether or not the property holds in that system. For this reason, probabilistic model checking provide rigorous guarantees. So far, however, probabilistic model checking has focused on propositional models where a state is represented by a symbol. On the other hand, it is commonly required to make relational abstractions in planning and reinforcement learning. Various frameworks handle …
We introduce reinforcement learning for heterogeneous teams in which rewards for an agent are additively factored into local costs, stimuli unique to each agent, and global rewards, those shared by all agents in the domain. Motivating domains include coordination of varied robotic platforms, which incur different costs for the same action, but share an overall goal. We present two templates for learning in this setting with factored rewards: a generalization of Perkins' Monte Carlo exploring starts for POMDPs to canonical MPOMDPs, with a single policy mapping joint observations of all agents t…
University of Michigan（密歇根大学）；UC Berkeley（加州大学伯克利分校）
First-person object-interaction tasks in high-fidelity, 3D, simulated environments such as the AI2Thor virtual home-environment pose significant sample-efficiency challenges for reinforcement learning (RL) agents learning from sparse task rewards. To alleviate these challenges, prior work has provided extensive supervision via a combination of reward-shaping, ground-truth object-information, and expert demonstrations. In this work, we show that one can learn object-interaction tasks from scratch without supervision by learning an attentive object-model as an auxiliary task during task learning…
GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning
Technical University of Darmstadt（达姆施塔特技术大学）；Google Intrinsic（谷歌内在）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Centre for Cognitive Science, TU Darmstadt（达姆施塔特技术大学认知科学中心）
School of Electronic and Information Engineering, Beijing Jiaotong University（北京交通大学电子信息工程学院）；State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University（北京交通大学轨道交通控制与安全国家重点实验室）
High-level driving behavior decision-making is an open-challenging problem for connected vehicle technology, especially in heterogeneous traffic scenarios. In this paper, a deep reinforcement learning based high-level driving behavior decision-making approach is proposed for connected vehicle in heterogeneous traffic situations. The model is composed of three main parts: a data preprocessor that maps hybrid data into a data format called hyper-grid matrix, a two-stream deep neural network that extracts the hidden features, and a deep reinforcement learning network that learns the optimal polic…
AAII,University of Technology Sydney（悉尼科技大学AAII）；National University of Singapore（新加坡国立大学）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织数据61研究所）
Numerous deep reinforcement learning agents have been proposed, and each of them has its strengths and flaws. In this work, we present a Cooperative Heterogeneous Deep Reinforcement Learning (CHDRL) framework that can learn a policy by integrating the advantages of heterogeneous agents. Specifically, we propose a cooperative learning framework that classifies heterogeneous agents into two classes: global agents and local agents. Global agents are off-policy agents that can utilize experiences from the other agents. Local agents are either on-policy agents or population-based evolutionary algor…
Alexa AI, Amazon Inc（亚马逊公司Alexa人工智能部门）；University of Southern California（南加州大学）
We propose a multimodal (vision-and-language) benchmark for cooperative and heterogeneous multi-agent learning. We introduce a benchmark multimodal dataset with tasks involving collaboration between multiple simulated heterogeneous robots in a rich multi-room home environment. We provide an integrated learning framework, multimodal implementations of state-of-the-art multi-agent reinforcement learning techniques, and a consistent evaluation protocol. Our experiments investigate the impact of different modalities on multi-agent learning performance. We also introduce a simple message passing me…
Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification
School of Electrical and Electronic Engineering（电子与电气工程学院）；Nanyang Technological University（南洋理工大学）；Singapore Institute of Manufacturing Technology (SIMTech)（新加坡制造技术研究所）
National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）；Shandong University（山东大学）
Recently, there is an emerging trend to apply deep reinforcement learning to solve the vehicle routing problem (VRP), where a learnt policy governs the selection of next node for visiting. However, existing methods could not handle well the pairing and precedence relationships in the pickup and delivery problem (PDP), which is a representative variant of VRP. To address this challenging issue, we leverage a novel neural network integrated with a heterogeneous attention mechanism to empower the policy in deep reinforcement learning to automatically select the nodes. In particular, the heterogen…
This paper presents the extension of the idea of spectrum sharing in the vehicular networks towards the Heterogeneous Vehicular Network(HetVNET) based on multi-agent reinforcement learning. Here, the multiple vehicle-to-vehicle(V2V) links reuse the spectrum of other vehicle-to-interface(V2I) and also those of other networks. The fast-changing environment in vehicular networks limits the idea of centralizing the CSI and allocate the channels. So, the idea of implementing ML-based methods is used here so that it can be implemented in a distributed manner in all vehicles. Here each On-Board Unit(…
Inspired by recent advances in agent communication with graph neural networks, this work proposes the representation of multi-agent communication capabilities as a directed labeled heterogeneous agent graph, in which node labels denote agent classes and edge labels, the communication type between two classes of agents. We also introduce a neural network architecture that specializes communication in fully cooperative heterogeneous multi-agent tasks by learning individual transformations to the exchanged messages between each pair of agent classes. By also employing encoding and action selectio…
Cooperative multi-robot tasks can benefit from heterogeneity in the robots' physical and behavioral traits. In spite of this, traditional Multi-Agent Reinforcement Learning (MARL) frameworks lack the ability to explicitly accommodate policy heterogeneity, and typically constrain agents to share neural network parameters. This enforced homogeneity limits application in cases where the tasks benefit from heterogeneous behaviors. In this paper, we crystallize the role of heterogeneity in MARL policies. Towards this end, we introduce Heterogeneous Graph Neural Network Proximal Policy Optimization …
Heterogeneous radio access networks require efficient traffic steering methods to reach near-optimal results in order to maximize network capacity. This paper aims to propose a novel traffic steering algorithm for usage in HetNets, which utilizes a reinforcement learning algorithm in combination with an artificial neural network to maximize total user satisfaction in the simulated cellular network. The novel algorithm was compared with two reference algorithms using network simulation results. The results prove that the novel algorithm provides noticeably better efficiency in comparison with r…
The transition from defined benefit to defined contribution pension plans shifts the responsibility for saving toward retirement from governments and institutions to the individuals. Determining optimal saving and investment strategy for individuals is paramount for stable financial stance and for avoiding poverty during work-life and retirement, and it is a particularly challenging task in a world where form of employment and income trajectory experienced by different occupation groups are highly diversified. We introduce a model in which agents learn optimal portfolio allocation and saving s…
Ohio State University（俄亥俄州立大学）；Air Force Research Laboratory（空军研究实验室）
We present an approach for reconfiguration of dynamic visual sensor networks with deep reinforcement learning (RL). Our RL agent uses a modified asynchronous advantage actor-critic framework and the recently proposed Relational Network module at the foundation of its network architecture. To address the issue of sample inefficiency in current approaches to model-free reinforcement learning, we train our system in an abstract simulation environment that represents inputs from a dynamic scene. Our system is validated using inputs from a real-world scenario and preexisting object detection and tr…
Object-centric representations have recently enabled significant progress in tackling relational reasoning tasks. By building a strong object-centric inductive bias into neural architectures, recent efforts have improved generalization and data efficiency of machine learning algorithms for these problems. One problem class involving relational reasoning that still remains under-explored is multi-agent reinforcement learning (MARL). Here we investigate whether object-centric representations are also beneficial in the fully cooperative MARL setting. Specifically, we study two ways of incorporati…
Bank of England（英格兰银行）；University College London（伦敦大学学院）；Office for National Statistics（英国国家统计局）
General equilibrium macroeconomic models are a core tool used by policymakers to understand a nation's economy. They represent the economy as a collection of forward-looking actors whose behaviours combine, possibly with stochastic effects, to determine global variables (such as prices) in a dynamic equilibrium. However, standard semi-analytical techniques for solving these models make it difficult to include the important effects of heterogeneous economic actors. The COVID-19 pandemic has further highlighted the importance of heterogeneity, for example in age and sector of employment, in macr…
Heterogeneous Multi-Agent Reinforcement Learning for Distributed Channel Access in WLANs
National Mobile Communications Research Laboratory, Southeast University（东南大学国家移动通信研究中心）；Purple Mountain Laboratories（紫金山实验室）；College of Electronics and Information Engineering, Shenzhen University（深圳大学电子与信息工程学院）；Wireless Technology Lab, 2012 Laboratories, Huawei Technologies Company Ltd.（华为技术有限公司无线技术实验室）；ITP Lab, the Department of Electrical and Electronic Engineering, Imperial College London（伦敦帝国理工学院电子与电气工程系ITP实验室）
Northwestern University（西北大学）；Yale University（耶鲁大学）；University of California, Berkeley（加州大学伯克利分校）
We study a heterogeneous agent macroeconomic model with an infinite number of households and firms competing in a labor market. Each household earns income and engages in consumption at each time step while aiming to maximize a concave utility subject to the underlying market conditions. The households aim to find the optimal saving strategy that maximizes their discounted cumulative utility given the market condition, while the firms determine the market conditions through maximizing corporate profit based on the household population behavior. The model captures a wide range of applications i…
Structural Reinforcement Learning for Heterogeneous Agent Macroeconomics
University of Zurich and SFI（苏黎世大学和SFI）；Peking University, School of Computer Science and BIGAI（北京大学计算机学院和BIGAI）；UC Berkeley（加州大学伯克利分校）；London School of Economics（伦敦经济学院）
New York University（纽约大学）；North Carolina State University（北卡罗来纳州立大学）；University of California, Berkeley（加利福尼亚大学伯克利分校）
Reinforcement Learning (RL) has the promise of providing data-driven support for decision-making in a wide range of problems in healthcare, education, business, and other domains. Classical RL methods focus on the mean of the total return and, thus, may provide misleading results in the setting of the heterogeneous populations that commonly underlie large-scale datasets. We introduce the K-Heterogeneous Markov Decision Process (K-Hetero MDP) to address sequential decision problems with population heterogeneity. We propose the Auto-Clustered Policy Evaluation (ACPE) for estimating the value of …
Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）；University of Oxford（牛津大学）；University College London（伦敦大学学院）；ReLER, AAII, University of Technology Sydney（悉尼科技大学AAII ReLER实验室）
School of Computer and Information Technology, Beijing Jiaotong University（北京交通大学计算机与信息技术学院）；Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University（北京交通大学交通数据分析与挖掘北京市重点实验室）
Energy consumption is one of the most critical concerns in designing computing devices, ranging from portable embedded systems to computer cluster systems. Furthermore, in the past decade, cluster systems have increasingly risen as popular platforms to run computing-intensive real-time applications in which the performance is of great importance. However, due to different characteristics of real-time workloads, developing general job scheduling solutions that efficiently address both energy consumption and performance in real-time cluster systems is a challenging problem. In this paper, inspir…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
The problem of scheduling of workloads onto heterogeneous processors (e.g., CPUs, GPUs, FPGAs) is of fundamental importance in modern data centers. Current system schedulers rely on application/system-specific heuristics that have to be built on a case-by-case basis. Recent work has demonstrated ML techniques for automating the heuristic search by using black-box approaches which require significant training data and time, which make them challenging to use in practice. This paper presents Symphony, a scheduling framework that addresses the challenge in two ways: (i) a domain-driven Bayesian r…
