We study the reinforcement learning problem in the setting of finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and episode length $H$. We propose a model-free algorithm UCB-Advantage and prove that it achieves $\tilde{O}(\sqrt{H^2SAT})$ regret where $T = KH$ and $K$ is the number of episodes to play. Our regret bound improves upon the results of [Jin et al., 2018] and matches the best known model-based algorithms as well as the information theoretic lower bound up to logarithmic factors. We also show that UCB-Advantage achieves low local switching cost and applies to concurrent reinforcement learning, improving upon the recent results of [Bai et al., 2019].
This paper presents a novel model-reference reinforcement learning control method for uncertain autonomous surface vehicles. The proposed control combines a conventional control method with deep reinforcement learning. With the conventional control, we can ensure the learning-based control law provides closed-loop stability for the overall system, and potentially increase the sample efficiency of the deep reinforcement learning. With the reinforcement learning, we can directly learn a control law to compensate for modeling uncertainties. In the proposed control, a nominal system is employed fo…
This paper presents a novel model-reference reinforcement learning algorithm for the intelligent tracking control of uncertain autonomous surface vehicles with collision avoidance. The proposed control algorithm combines a conventional control method with reinforcement learning to enhance control accuracy and intelligence. In the proposed control design, a nominal system is considered for the design of a baseline tracking controller using a conventional control approach. The nominal system also defines the desired behaviour of uncertain autonomous surface vehicles in an obstacle-free environme…
Bowling Green State University（博林格林州立大学）；University of Ottawa（渥太华大学）；Machine Intelligence Research Labs（机器智能研究实验室）
Model-reference adaptive systems refer to a consortium of techniques that guide plants to track desired reference trajectories. Approaches based on theories like Lyapunov, sliding surfaces, and backstepping are typically employed to advise adaptive control strategies. The resulting solutions are often challenged by the complexity of the reference model and those of the derived control strategies. Additionally, the explicit dependence of the control strategies on the process dynamics and reference dynamical models may contribute in degrading their efficiency in the face of uncertain or unknown …
Tsinghua-Berkeley Shenzhen Institute, Tsinghua University（清华大学清华-伯克利深圳学院）；Shanghai University of Electric Power（上海电力大学）；Tsinghua University（清华大学）；Beihang University（北京航空航天大学）
Reference-model-assisted deep reinforcement learning (DRL) for inverter-based Volt-Var Control (IB-VVC) in active distribution networks is proposed. We investigate that a large action space increases the learning difficulties of DRL and degrades the optimization performance in the process of generating data and training neural networks. To reduce the action space of DRL, we design a reference-model-assisted DRL approach. We introduce definitions of the reference model, reference-model-based optimization, and reference actions. The reference-model-assisted DRL learns the residual actions betwee…
Huawei R&D UK（华为英国研发部）；Technische Universität Darmstadt（达姆施塔特工业大学）；University College London（伦敦大学学院）
Satisfying safety constraints almost surely (or with probability one) can be critical for the deployment of Reinforcement Learning (RL) in real-life applications. For example, plane landing and take-off should ideally occur with probability one. We address the problem by introducing Safety Augmented (Saute) Markov Decision Processes (MDPs), where the safety constraints are eliminated by augmenting them into the state-space and reshaping the objective. We show that Saute MDP satisfies the Bellman equation and moves us closer to solving Safe RL with constraints satisfied almost surely. We argue …
Universidad de la República（共和国大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
We consider the problem of finding optimal policies for a Markov Decision Process with almost sure constraints on state transitions and action triplets. We define value and action-value functions that satisfy a barrier-based decomposition which allows for the identification of feasible policies independently of the reward process. We prove that, given a policy π, certifying whether certain state-action pairs lead to feasible trajectories under π is equivalent to solving an auxiliary problem aimed at finding the probability of performing an unfeasible transition. Using this interpretation,we de…
KL-regularized reinforcement learning from expert demonstrations has proved successful in improving the sample efficiency of deep reinforcement learning algorithms, allowing them to be applied to challenging physical real-world tasks. However, we show that KL-regularized reinforcement learning with behavioral reference policies derived from expert demonstrations can suffer from pathological training dynamics that can lead to slow, unstable, and suboptimal online learning. We show empirically that the pathology occurs for commonly chosen behavioral policy classes and demonstrate its impact on s…
Model-free control based on the idea of Reinforcement Learning is a promising approach that has recently gained extensive attention. However, Reinforcement-Learning-based control methods solely focus on the regulation problem or learn to track a reference that is generated by a time-invariant exo-system. In the latter case, controllers are only able to track the time-invariant reference dynamics which they have been trained on and need to be re-trained each time the reference dynamics change. Consequently, these methods fail in a number of applications which obviously rely on a trajectory not …
Reinforcement learning (RL) is a promising, upcoming topic in automatic control applications. Where classical control approaches require a priori system knowledge, data-driven control approaches like RL allow a model-free controller design procedure, rendering them emergent techniques for systems with changing plant structures and varying parameters. While it was already shown in various applications that the transient control behavior for complex systems can be sufficiently handled by RL, the challenge of non-vanishing steady-state control errors remains, which arises from the usage of contro…
University of Liverpool（利物浦大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）
We provide the first solution for model-free reinforcement learning of ω-regular objectives for Markov decision processes (MDPs). We present a constructive reduction from the almost-sure satisfaction of ω-regular objectives to an almost- sure reachability problem and extend this technique to learning how to control an unknown model so that the chance of satisfying the objective is maximized. A key feature of our technique is the compilation of ω-regular properties into limit- deterministic Buechi automata instead of the traditional Rabin automata; this choice sidesteps difficulties that have m…
This document is a concise summary of many key results in single-agent reinforcement learning (RL). The intended audience are those who already have some familiarity with RL and are looking to review, reference and/or remind themselves of important ideas in the field.
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；IAV GmbH（IAV有限公司）
In recent years, reinforcement learning (RL) has gained increasing attention in control engineering. Especially, policy gradient methods are widely used. In this work, we improve the tracking performance of proximal policy optimization (PPO) for arbitrary reference signals by incorporating information about future reference values. Two variants of extending the argument of the actor and the critic taking future reference values into account are presented. In the first variant, global future reference values are added to the argument. For the second variant, a novel kind of residual space with …
NVIDIA Research（英伟达研究院）；Technion - Israel Institute of Technology（以色列理工学院）；Indian Institute of Technology, Indore（印度理工学院印多尔分校）
In recent years, there has been significant progress in applying deep reinforcement learning (RL) for solving challenging problems across a wide variety of domains. Nevertheless, convergence of various methods has been shown to suffer from inconsistencies, due to algorithmic instability and variance, as well as stochasticity in the benchmark environments. Particularly, despite the fact that the agent's performance may be improving on average, it may abruptly deteriorate at late stages of training. In this work, we study methods for enhancing the agent's learning process, by providing conservat…
Johns Hopkins University（约翰斯·霍普金斯大学）；Universidad de la República（共和国大学）
In this work we address the problem of finding feasible policies for Constrained Markov Decision Processes under probability one constraints. We argue that stationary policies are not sufficient for solving this problem, and that a rich class of policies can be found by endowing the controller with a scalar quantity, so called budget, that tracks how close the agent is to violating the constraint. We show that the minimal budget required to act safely can be obtained as the smallest fixed point of a Bellman-like operator, for which we analyze its convergence properties. We also show how to lea…
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…
University of Oxford（牛津大学）；Microsoft Research（微软研究院）；Google（谷歌）；Deepmind（深度思维）
Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of which adopt a sequence generation paradigm similar to neural machine translation, in which sequence-to-sequence models are trained to maximize the likelihood of known reference programs. While achieving impressive results, this strategy has two key limitations. First, it ignores Program Aliasing: the fact that many different programs may satisfy a given specification (especially with incomplete speci…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
This paper proposes a new robust update rule of target network for deep reinforcement learning (DRL), to replace the conventional update rule, given as an exponential moving average. The target network is for smoothly generating the reference signals for a main network in DRL, thereby reducing learning variance. The problem with its conventional update rule is the fact that all the parameters are smoothly copied with the same speed from the main network, even when some of them are trying to update toward the wrong directions. This behavior increases the risk of generating the wrong reference s…
Ubiquitous Knowledge Processing Lab (UKP-TUDA)（泛在知识处理实验室（UKP-TUDA））；Technische Universität Darmstadt（达姆施塔特工业大学）
We propose a method to perform automatic document summarisation without using reference summaries. Instead, our method interactively learns from users' preferences. The merit of preference-based interactive summarisation is that preferences are easier for users to provide than reference summaries. Existing preference-based interactive learning methods suffer from high sample complexity, i.e. they need to interact with the oracle for many rounds in order to converge. In this work, we propose a new objective function, which enables us to leverage active learning, preference learning and reinforc…
Information Technology R&D Center, Mitsubishi Electric Corporation（三菱电机株式会社信息技术研发中心）；National Institute of Advanced Industrial Science and Technology (AIST)（日本先进产业科学技术研究所（AIST））；Mitsubishi Electric Research Labs（三菱电机研究实验室）
In this paper, we consider the problem of building learning agents that can efficiently learn to navigate in constrained environments. The main goal is to design agents that can efficiently learn to understand and generalize to different environments using high-dimensional inputs (a 2D map), while following feasible paths that avoid obstacles in obstacle-cluttered environment. To achieve this, we make use of traditional path planning algorithms, supervised learning, and reinforcement learning algorithms in a synergistic way. The key idea is to decouple the navigation problem into planning and …
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Smith College（史密斯学院）
Evaluation of deep reinforcement learning (RL) is inherently challenging. In particular, learned policies are largely opaque, and hypotheses about the behavior of deep RL agents are difficult to test in black-box environments. Considerable effort has gone into addressing opacity, but almost no effort has been devoted to producing high quality environments for experimental evaluation of agent behavior. We present TOYBOX, a new high-performance, open-source* subset of Atari environments re-designed for the experimental evaluation of deep RL. We show that TOYBOX enables a wide range of experiment…
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Beijing University of Posts and Telecommunications（北京邮电大学）
Deep reinforcement learning (RL) has been a commonly-used strategy for the abstractive summarization task to address both the exposure bias and non-differentiable task issues. However, the conventional reward Rouge-L simply looks for exact n-grams matches between candidates and annotated references, which inevitably makes the generated sentences repetitive and incoherent. In this paper, instead of Rouge-L, we explore the practicability of utilizing the distributional semantics to measure the matching degrees. With distributional semantics, sentence-level evaluation can be obtained, and semanti…
Information Technology R&D Center, Mitsubishi Electric Corporation（三菱电机公司信息技术研发中心）；Mitsubishi Electric Research Labs（三菱电机研究实验室）；Mitsubishi Electric Corp（三菱电机公司）
In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known. Generating smooth, dynamically feasible trajectories could be difficult for such systems. Using sampling-based algorithms for motion planning may result in trajectories that are prone to undesirable control jumps. However, they can usually provide a good reference trajectory which a model-free reinforcement learning algorithm can then exploit by limiting the se…
A generic and scalable Reinforcement Learning scheme for Artificial Neural Networks is presented, providing a general purpose learning machine. By reference to a node threshold three features are described 1) A mechanism for Primary Reinforcement, capable of solving linearly inseparable problems 2) The learning scheme is extended to include a mechanism for Conditioned Reinforcement, capable of forming long term strategy 3) The learning scheme is modified to use a threshold-based deep learning algorithm, providing a robust and biologically inspired alternative to backpropagation. The model may …
Inverse Reinforcement Learning (IRL) algorithms infer a reward function that explains demonstrations provided by an expert acting in the environment. Maximum Causal Entropy (MCE) IRL is currently the most popular formulation of IRL, with numerous extensions. In this tutorial, we present a compressed derivation of MCE IRL and the key results from contemporary implementations of MCE IRL algorithms. We hope this will serve both as an introductory resource for those new to the field, and as a concise reference for those already familiar with these topics.
Universidad de Santiago de Chile (USACH)（圣地亚哥大学（USACH））；Center for the Development of Nanoscience and Nanotechnology（纳米科学与纳米技术发展中心）；University of the Basque Country UPV/EHU（巴斯克大学（UPV/EHU））；IKERBASQUE, Basque Foundation for Science（巴斯克科学基金会（IKERBASQUE））；Shanghai University（上海大学）
Machine learning employs dynamical algorithms that mimic the human capacity to learn, where the reinforcement learning ones are among the most similar to humans in this respect. On the other hand, adaptability is an essential aspect to perform any task efficiently in a changing environment, and it is fundamental for many purposes, such as natural selection. Here, we propose an algorithm based on successive measurements to adapt one quantum state to a reference unknown state, in the sense of achieving maximum overlap. The protocol naturally provides many identical copies of the reference state,…
McGill University（麦吉尔大学）；Mila - Quebec Artificial Intelligence Institute（魁北克人工智能研究所（Mila））；Université du Québec à Montréal（魁北克大学蒙特利尔分校）；Facebook AI Research（Facebook人工智能研究）；CIFAR AI chair（CIFAR人工智能主席职位）；DeepMind；Université de Montréal（蒙特利尔大学）
We propose a general framework for policy representation for reinforcement learning tasks. This framework involves finding a low-dimensional embedding of the policy on a reproducing kernel Hilbert space (RKHS). The usage of RKHS based methods allows us to derive strong theoretical guarantees on the expected return of the reconstructed policy. Such guarantees are typically lacking in black-box models, but are very desirable in tasks requiring stability. We conduct several experiments on classic RL domains. The results confirm that the policies can be robustly embedded in a low-dimensional space…
Low-thrust trajectory design and in-flight control remain two of the most challenging topics for new-generation satellite operations. Most of the solutions currently implemented are based on reference trajectories and lead to sub-optimal fuel usage. Other solutions are based on simple guidance laws that need to be updated periodically, increasing the cost of operations. Whereas some optimization strategies leverage Artificial Intelligence methods, all of the approaches studied so far need either previously generated data or a strong a priori knowledge of the satellite dynamics. This study uses…
A Domain-Knowledge-Aided Deep Reinforcement Learning Approach for Flight Control Design
School of Aerospace, Transport and Manufacturing, Cranfield University（克兰菲尔德大学航空、运输与制造学院）；School of Aerospace Engineering, Beijing Institute of Technology（北京理工大学航空航天学院）
University of York（约克大学）；L3S Research Center, Leibniz University Hannover（莱布尼茨汉诺威大学L3S研究中心）
Potential Based Reward Shaping combined with a potential function based on appropriately defined abstract knowledge has been shown to significantly improve learning speed in Reinforcement Learning. MultiGrid Reinforcement Learning (MRL) has further shown that such abstract knowledge in the form of a potential function can be learned almost solely from agent interaction with the environment. However, we show that MRL faces the problem of not extending well to work with Deep Learning. In this paper we extend and improve MRL to take advantage of modern Deep Learning algorithms such as Deep Q-Netw…
The offline reinforcement learning (RL) problem is often motivated by the need to learn data-driven decision policies in financial, legal and healthcare applications. However, the learned policy could retain sensitive information of individuals in the training data (e.g., treatment and outcome of patients), thus susceptible to various privacy risks. We design offline RL algorithms with differential privacy guarantees which provably prevent such risks. These algorithms also enjoy strong instance-dependent learning bounds under both tabular and linear Markov decision process (MDP) settings. Our …
Federated Distributional Reinforcement Learning with Distributional Critic Regularization
Dept. of Mechanical Engineering, Rochester Institute of Technology（机械工程系，罗切斯特理工学院）；Dept. of Psychology and School of Information, Rochester Institute of Technology（心理学系和信息学院，罗切斯特理工学院）；Department of Engineering Science, University West（工程科学系，西大学）；Golisano College of Computing and Information Sciences, Rochester Institute of Technology（计算与信息科学学院，罗切斯特理工学院）
CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction
University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）；North Carolina Battery Complexity, Autonomous Vehicle and Electrification (BATT CAVE) Research Center（北卡罗来纳州电池复杂性、自动驾驶与电气化（BATT CAVE）研究中心）
