Reinforcement learning (RL) methods often rely on massive exploration data to search optimal policies, and suffer from poor sampling efficiency. This paper presents a mixed reinforcement learning (mixed RL) algorithm by simultaneously using dual representations of environmental dynamics to search the optimal policy with the purpose of improving both learning accuracy and training speed. The dual representations indicate the environmental model and the state-action data: the former can accelerate the learning process of RL, while its inherent model uncertainty generally leads to worse policy accuracy than the latter, which comes from direct measurements of states and actions. In the framework design of the mixed RL, the compensation of the additive stochastic model uncertainty is embedded inside the policy iteration RL framework by using explored state-action data via iterative Bayesian estimator (IBE). The optimal policy is then computed in an iterative way by alternating between policy evaluation (PEV) and policy improvement (PIM). The convergence of the mixed RL is proved using the Bellman's principle of optimality, and the recursive stability of the generated policy is proved via the Lyapunov's direct method. The effectiveness of the mixed RL is demonstrated by a typical optimal control problem of stochastic non-affine nonlinear systems (i.e., double lane change task with an automated vehicle).
The COVID-19 pandemic has highlighted the importance of supply chains and the role of digital management to react to dynamic changes in the environment. In this work, we focus on developing dynamic inventory ordering policies for a multi-echelon, i.e. multi-stage, supply chain. Traditional inventory optimization methods aim to determine a static reordering policy. Thus, these policies are not able to adjust to dynamic changes such as those observed during the COVID-19 crisis. On the other hand, conventional strategies offer the advantage of being interpretable, which is a crucial feature for s…
Norwegian University of Technology, NTNU（挪威科技大学（NTNU））；IMT School for Advanced Studies Lucca（卢卡IMT高等研究院）
Model Predictive Control has been recently proposed as policy approximation for Reinforcement Learning, offering a path towards safe and explainable Reinforcement Learning. This approach has been investigated for Q-learning and actor-critic methods, both in the context of nominal Economic MPC and Robust (N)MPC, showing very promising results. In that context, actor-critic methods seem to be the most reliable approach. Many applications include a mixture of continuous and integer inputs, for which the classical actor-critic methods need to be adapted. In this paper, we present a policy approxim…
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；College of Information Engineering, Shenzhen University（深圳大学信息工程学院）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；Alibaba Group（阿里巴巴集团）
Recent research has shown that non-additive image steganographic frameworks effectively improve security performance through adjusting distortion distribution. However, as far as we know, all of the existing non-additive proposals are based on handcrafted policies, and can only be applied to a specific image domain, which heavily prevent non-additive steganography from releasing its full potentiality. In this paper, we propose an automatic non-additive steganographic distortion learning framework called MCTSteg to remove the above restrictions. Guided by the reinforcement learning paradigm, we…
We propose a model-free reinforcement learning method for controlling mixed autonomy traffic in simulated traffic networks with through-traffic-only two-way and four-way intersections. Our method utilizes multi-agent policy decomposition which allows decentralized control based on local observations for an arbitrary number of controlled vehicles. We demonstrate that, even without reward shaping, reinforcement learning learns to coordinate the vehicles to exhibit traffic signal-like behaviors, achieving near-optimal throughput with 33-50% controlled vehicles. With the help of multi-task learnin…
Process optimization for metal additive manufacturing (AM) is crucial to ensure repeatability, control microstructure, and minimize defects. Despite efforts to address this via the traditional design of experiments and statistical process mapping, there is limited insight on an on-the-fly optimization framework that can be integrated into a metal AM system. Additionally, most of these methods, being data-intensive, cannot be supported by a metal AM alloy or system due to budget restrictions. To tackle this issue, the article introduces a Reinforcement Learning (RL) methodology transformed into…
Virginia Tech（弗吉尼亚理工学院暨州立大学）；New Jersey Institute of Technology（新泽西理工学院）；IoTeX
Additive Manufacturing (AM) is a powerful technology that produces complex 3D geometries using various materials in a layer-by-layer fashion. However, quality assurance is the main challenge in AM industry due to the possible time-varying processing conditions during AM process. Notably, new defects may occur during printing, which cannot be mitigated by offline analysis tools that focus on existing defects. This challenge motivates this work to develop online learning-based methods to deal with the new defects during printing. Since AM typically fabricates a small number of customized product…
Recent research has shown that map raw pixels from a single front-facing camera directly to steering commands are surprisingly powerful. This paper presents a convolutional neural network (CNN) to playing the CarRacing-v0 using imitation learning in OpenAI Gym. The dataset is generated by playing the game manually in Gym and used a data augmentation method to expand the dataset to 4 times larger than before. Also, we read the true speed, four ABS sensors, steering wheel position, and gyroscope for each image and designed a mixed model by combining the sensor input and image input. After traini…
Institute for Intelligent Systems Research and Innovation（智能系统研究与创新研究所）；Deakin University（迪肯大学）
In 2015, Google's DeepMind announced an advancement in creating an autonomous agent based on deep reinforcement learning (DRL) that could beat a professional player in a series of 49 Atari games. However, the current manifestation of DRL is still immature, and has significant drawbacks. One of DRL's imperfections is its lack of "exploration" during the training process, especially when working with high-dimensional problems. In this paper, we propose a mixed strategy approach that mimics behaviors of human when interacting with environment, and create a "thinking" agent that allows for more ef…
Deep reinforcement learning has led to several recent breakthroughs, though the learned policies are often based on black-box neural networks. This makes them difficult to interpret and to impose desired specification constraints during learning. We present an iterative framework, MORL, for improving the learned policies using program synthesis. Concretely, we propose to use synthesis techniques to obtain a symbolic representation of the learned policy, which can then be debugged manually or automatically using program repair. After the repair step, we use behavior cloning to obtain the policy…
Autonomous driving promises to transform road transport. Multi-vehicle and multi-lane scenarios, however, present unique challenges due to constrained navigation and unpredictable vehicle interactions. Learning-based methods---such as deep reinforcement learning---are emerging as a promising approach to automatically design intelligent driving policies that can cope with these challenges. Yet, the process of safely learning multi-vehicle driving behaviours is hard: while collisions---and their near-avoidance---are essential to the learning process, directly executing immature policies on auton…
Laser Scan Path Design for Controlled Microstructure in Additive Manufacturing with Integrated Reduced-Order Phase-Field Modeling and Deep Reinforcement Learning
Computational Science Program, The University of Texas at El Paso（德克萨斯理工大学计算科学计划）；Department of Aerospace and Mechanical Engineering, The University of Texas at El Paso（德克萨斯理工大学航空航天与机械工程系）；School of Manufacturing Systems and Networks, Arizona State University（亚利桑那州立大学制造系统与网络学院）
Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with evolutionary reinforcement learning (MAPPER) method to learn an effective local planning policy in mixed dynamic environments. Reinforcement learning-based methods usually suffer performance degradation on long-horizon tasks with goal-conditioned sparse rewards, so we decompose the long-range navigation task into many easier sub-tasks under the guidance of a glo…
Digital Twin Synchronization: Bridging the Sim-RL Agent to a Real-Time Robotic Additive Manufacturing Control
Department of Mechanical Engineering, University of Louisiana at Lafayette（路易斯安那大学拉斐特分校机械工程系）；Computer Science & Information Systems Department, Bradley University（布雷纳德大学计算机科学与信息系统系）
In this work, we propose a deep reinforcement learning (DRL) model for finding a feasible solution for (mixed) integer programming (MIP) problems. Finding a feasible solution for MIP problems is critical because many successful heuristics rely on a known initial feasible solution. However, it is in general NP-hard. Inspired by the feasibility pump (FP), a well-known heuristic for searching feasible MIP solutions, we develop a smart feasibility pump (SFP) method using DRL. In addition to multi-layer perception (MLP), we propose a novel convolution neural network (CNN) structure for the policy n…
Zenseact AB（Zenseact公司）；Chalmers University of Technology（查尔姆斯理工大学）；Scool INRIA Lille-Nord Europe（法国国家信息与自动化研究所里尔-北欧洲Scool团队）；CRIStAL, CNRS（法国国家科学研究中心CRIStAL实验室）；University of Neuchatel（纳沙泰尔大学）；University of Oslo（奥斯陆大学）
In this paper, we consider risk-sensitive sequential decision-making in Reinforcement Learning (RL). Our contributions are two-fold. First, we introduce a novel and coherent quantification of risk, namely composite risk, which quantifies the joint effect of aleatory and epistemic risk during the learning process. Existing works considered either aleatory or epistemic risk individually, or as an additive combination. We prove that the additive formulation is a particular case of the composite risk when the epistemic risk measure is replaced with expectation. Thus, the composite risk is more sen…
Xi’an Jiaotong University（西安交通大学）；The Hong Kong Polytechnic University（香港理工大学）
Mixed-precision quantization mostly predetermines the model bit-width settings before actual training due to the non-differential bit-width sampling process, obtaining sub-optimal performance. Worse still, the conventional static quality-consistent training setting, i.e., all data is assumed to be of the same quality across training and inference, overlooks data quality changes in real-world applications which may lead to poor robustness of the quantized models. In this paper, we propose a novel Data Quality-aware Mixed-precision Quantization framework, dubbed DQMQ, to dynamically adapt quanti…
University of Science and Technology of China（中国科学技术大学）；University of Alberta（阿尔伯塔大学）
This paper investigates the optimal control problem for a class of discrete-time stochastic systems subject to additive and multiplicative noises. A stochastic Lyapunov equation and a stochastic algebra Riccati equation are established for the existence of the optimal admissible control policy. A model-free reinforcement learning algorithm is proposed to learn the optimal admissible control policy using the data of the system states and inputs without requiring any knowledge of the system matrices. It is proven that the learning algorithm converges to the optimal admissible control policy. The…
The transition from today's mostly human-driven traffic to a purely automated one will be a gradual evolution, with the effect that we will likely experience mixed traffic in the near future. Connected and automated vehicles can benefit human-driven ones and the whole traffic system in different ways, for example by improving collision avoidance and reducing traffic waves. Many studies have been carried out to improve intersection management, a significant bottleneck in traffic, with intelligent traffic signals or exclusively automated vehicles. However, the problem of how to improve mixed tra…
By using communication between multiple agents in multi-agent environments, one can reduce the effects of partial observability by combining one agent's observation with that of others in the same dynamic environment. While a lot of successful research has been done towards communication learning in cooperative settings, communication learning in mixed cooperative-competitive settings is also important and brings its own complexities such as the opposing team overhearing the communication. In this paper, we apply differentiable inter-agent learning (DIAL), designed for cooperative settings, to…
University of California at Riverside（加州大学河滨分校）；Beijing Jiaotong University（北京交通大学）
Taking advantage of both vehicle-to-everything (V2X) communication and automated driving technology, connected and automated vehicles are quickly becoming one of the transformative solutions to many transportation problems. However, in a mixed traffic environment at signalized intersections, it is still a challenging task to improve overall throughput and energy efficiency considering the complexity and uncertainty in the traffic system. In this study, we proposed a hybrid reinforcement learning (HRL) framework which combines the rule-based strategy and the deep reinforcement learning (deep RL…
Large-Scale Mixed-Traffic and Intersection Control using Multi-agent Reinforcement Learning
Department of Civil and Coastal Engineering at University of Florida（佛罗里达大学土木与海岸工程系）；Department of Computer Science at University of Memphis（密苏里大学计算机科学系）；Min H. Kao Department of Electrical Engineering and Computer Science at University of Tennessee（田纳西大学电子工程与计算机科学系）
Google Research（谷歌研究院）；University of Virginia（弗吉尼亚大学）；University of Chicago（芝加哥大学）
Incrementality, which is used to measure the causal effect of showing an ad to a potential customer (e.g. a user in an internet platform) versus not, is a central object for advertisers in online advertising platforms. This paper investigates the problem of how an advertiser can learn to optimize the bidding sequence in an online manner \emph{without} knowing the incrementality parameters in advance. We formulate the offline version of this problem as a specially structured episodic Markov Decision Process (MDP) and then, for its online learning counterpart, propose a novel reinforcement learn…
It is anticipated that the era of fully autonomous vehicle operations will be preceded by a lengthy "Transition Period" where the traffic stream will be mixed, that is, consisting of connected autonomous vehicles (CAVs), human-driven vehicles (HDVs) and connected human-driven vehicles (CHDVs). In recognition of the fact that public acceptance of CAVs will hinge on safety performance of automated driving systems, and that there will likely be safety challenges in the early part of the transition period, significant research efforts have been expended in the development of safety-conscious autom…
University of Science and Technology of China（中国科学技术大学）
This paper addresses the average cost minimization problem for discrete-time systems with multiplicative and additive noises via reinforcement learning. By using Q-function, we propose an online learning scheme to estimate the kernel matrix of Q-function and to update the control gain using the data along the system trajectories. The obtained control gain and kernel matrix are proved to converge to the optimal ones. To implement the proposed learning scheme, an online model-free reinforcement learning algorithm is given, where recursive least squares method is used to estimate the kernel matri…
M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality
Department of Informatics, King’s College London, London, United Kingdom（伦敦大学国王学院信息学系）；Societal Systems Department, Carnegie Mellon University, Pittsburgh, PA, USA（卡内基梅隆大学社会系统系）
FOVA: Offline Federated Reinforcement Learning with Mixed-Quality Data
School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；School of Cyber Science and Technology, Sun Yat-sen University（中山大学网络科学与技术学院）；Department of Computer Science and Technology, BNRist, Tsinghua University（清华大学计算机科学与技术系）；Zhongguancun Laboratory（中关村实验室）
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）；Macquarie University（麦考瑞大学）
We consider an offline reinforcement learning (RL) setting where the agent need to learn from a dataset collected by rolling out multiple behavior policies. There are two challenges for this setting: 1) The optimal trade-off between optimizing the RL signal and the behavior cloning (BC) signal changes on different states due to the variation of the action coverage induced by different behavior policies. Previous methods fail to handle this by only controlling the global trade-off. 2) For a given state, the action distribution generated by different behavior policies may have multiple modes. Th…
Optimal decision making with limited or no information in stochastic environments where multiple agents interact is a challenging topic in the realm of artificial intelligence. Reinforcement learning (RL) is a popular approach for arriving at optimal strategies by predicating stimuli, such as the reward for following a strategy, on experience. RL is heavily explored in the single-agent context, but is a nascent concept in multiagent problems. To this end, I propose several principled model-free and partially model-based reinforcement learning approaches for several multiagent settings. In the …
Robot assembly discovery is a challenging problem that lives at the intersection of resource allocation and motion planning. The goal is to combine a predefined set of objects to form something new while considering task execution with the robot-in-the-loop. In this work, we tackle the problem of building arbitrary, predefined target structures entirely from scratch using a set of Tetris-like building blocks and a robotic manipulator. Our novel hierarchical approach aims at efficiently decomposing the overall task into three feasible levels that benefit mutually from each other. On the high le…
Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model
School of Vehicle and Mobility, Tsinghua University（清华大学车辆与出行学院）；Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）
In offline reinforcement learning, a policy learns to maximize cumulative rewards with a fixed collection of data. Towards conservative strategy, current methods choose to regularize the behavior policy or learn a lower bound of the value function. However, exorbitant conservation tends to impair the policy's generalization ability and degrade its performance, especially for the mixed datasets. In this paper, we propose the method of reducing conservativeness oriented reinforcement learning. On the one hand, the policy is trained to pay more attention to the minority samples in the static data…
In this paper, we study the covariance steering (CS) problem for discrete-time linear systems subject to multiplicative and additive noise. Specifically, we consider two variants of the so-called CS problem. The goal of the first problem, which is called the exact CS problem, is to steer the mean and the covariance of the state process to their desired values in finite time. In the second one, which is called the ``relaxed'' CS problem, the covariance assignment constraint is relaxed into a positive semi-definite constraint. We show that the relaxed CS problem can be cast as an equivalent conv…
We consider a mixed autonomy scenario where the traffic intersection controller decides whether the traffic light will be green or red at each lane for multiple traffic-light blocks. The objective of the traffic intersection controller is to minimize the queue length at each lane and maximize the outflow of vehicles over each block. We consider that the traffic intersection controller informs the autonomous vehicle (AV) whether the traffic light will be green or red for the future traffic-light block. Thus, the AV can adapt its dynamics by solving an optimal control problem. We model the decis…
