A simple and natural algorithm for reinforcement learning (RL) is Monte Carlo Exploring Starts (MCES), where the Q-function is estimated by averaging the Monte Carlo returns, and the policy is improved by choosing actions that maximize the current estimate of the Q-function. Exploration is performed by "exploring starts", that is, each episode begins with a randomly chosen state and action, and then follows the current policy to the terminal state. In the classic book on RL by Sutton & Barto (2018), it is stated that establishing convergence for the MCES algorithm is one of the most important remaining open theoretical problems in RL. However, the convergence question for MCES turns out to be quite nuanced. Bertsekas & Tsitsiklis (1996) provide a counter-example showing that the MCES algorithm does not necessarily converge. Tsitsiklis (2002) further shows that if the original MCES algorithm is modified so that the Q-function estimates are updated at the same rate for all state-action pairs, and the discount factor is strictly less than one, then the MCES algorithm converges. In this paper we make headway with the original and more efficient MCES algorithm given in Sutton & Barto (1998), establishing almost sure convergence for Optimal Policy Feed-Forward MDPs, which are MDPs whose states are not revisited within any episode when using an optimal policy. Such MDPs include a large class of environments such as all deterministic environments and all episodic environments with a timestep or any monotonically changing values as part of the state. Different from the previous proofs using stochastic approximations, we introduce a novel inductive approach, which is very simple and only makes use of the strong law of large numbers.
University of Pennsylvania（宾夕法尼亚大学）；Vanderbilt University（范德堡大学）；Children’s Hospital of Philadelphia（费城儿童医院）
Long horizon robot learning tasks with sparse rewards pose a significant challenge for current reinforcement learning algorithms. A key feature enabling humans to learn challenging control tasks is that they often receive expert intervention that enables them to understand the high-level structure of the task before mastering low-level control actions. We propose a framework for leveraging expert intervention to solve long-horizon reinforcement learning tasks. We consider \emph{option templates}, which are specifications encoding a potential option that can be trained using reinforcement learn…
We propose a exploration mechanism of policy in Deep Reinforcement Learning, which is exploring more when agent needs, called Add Noise to Noise (AN2N). The core idea is: when the Deep Reinforcement Learning agent is in a state of poor performance in history, it needs to explore more. So we use cumulative rewards to evaluate which past states the agents have not performed well, and use cosine distance to measure whether the current state needs to be explored more. This method shows that the exploration mechanism of the agent's policy is conducive to efficient exploration. We combining the prop…
University of Maryland, College Park（马里兰大学帕克分校）；Swarm Labs（斯沃姆实验室）
Visualizing optimization landscapes has led to many fundamental insights in numeric optimization, and novel improvements to optimization techniques. However, visualizations of the objective that reinforcement learning optimizes (the "reward surface") have only ever been generated for a small number of narrow contexts. This work presents reward surfaces and related visualizations of 27 of the most widely used reinforcement learning environments in Gym for the first time. We also explore reward surfaces in the policy gradient direction and show for the first time that many popular reinforcement …
Rutgers University（罗格斯大学）；University of Alberta（阿尔伯塔大学）
This paper presents a new algorithm for online linear regression whose efficiency guarantees satisfy the requirements of the KWIK (Knows What It Knows) framework. The algorithm improves on the complexity bounds of the current state-of-the-art procedure in this setting. We explore several applications of this algorithm for learning compact reinforcement-learning representations. We show that KWIK linear regression can be used to learn the reward function of a factored MDP and the probabilities of action outcomes in Stochastic STRIPS and Object Oriented MDPs, none of which have been proven to be…
A basic simulation-based reinforcement learning algorithm is the Monte Carlo Exploring States (MCES) method, also known as optimistic policy iteration, in which the value function is approximated by simulated returns and a greedy policy is selected at each iteration. The convergence of this algorithm in the general setting has been an open question. In this paper, we investigate the convergence of this algorithm for the case with undiscounted costs, also known as the stochastic shortest path problem. The results complement existing partial results on this topic and thereby helps further settle…
ENSTA ParisTech（巴黎高等科技学院）；AKKA Technologies（阿卡科技公司）；Valeo Egypt（法雷奥埃及公司）；Valeo Vision Systems（法雷奥视觉系统公司）；Galway-Mayo Institute of Technology（戈尔韦-梅奥理工学院）
Deep Reinforcement Learning (DRL) has become increasingly powerful in recent years, with notable achievements such as Deepmind's AlphaGo. It has been successfully deployed in commercial vehicles like Mobileye's path planning system. However, a vast majority of work on DRL is focused on toy examples in controlled synthetic car simulator environments such as TORCS and CARLA. In general, DRL is still at its infancy in terms of usability in real-world applications. Our goal in this paper is to encourage real-world deployment of DRL in various autonomous driving (AD) applications. We first provide …
University of Göttingen（哥廷根大学）；University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；Canadian Institute for Advanced Research（加拿大高等研究院）
Computer-aided design of molecules has the potential to disrupt the field of drug and material discovery. Machine learning, and deep learning, in particular, have been topics where the field has been developing at a rapid pace. Reinforcement learning is a particularly promising approach since it allows for molecular design without prior knowledge. However, the search space is vast and efficient exploration is desirable when using reinforcement learning agents. In this study, we propose an algorithm to aid efficient exploration. The algorithm is inspired by a concept known in the literature as …
Institute for Robotics and Intelligent Machines（机器人与智能机器研究所）；Georgia Institute of Technology（佐治亚理工学院）
Deep reinforcement learning has been successful in a variety of tasks, such as game playing and robotic manipulation. However, attempting to learn \textit{tabula rasa} disregards the logical structure of many domains as well as the wealth of readily available knowledge from domain experts that could help "warm start" the learning process. We present a novel reinforcement learning technique that allows for intelligent initialization of a neural network weights and architecture. Our approach permits the encoding domain knowledge directly into a neural decision tree, and improves upon that knowle…
Leiden Institute of Advanced Computer Science, Leiden University（莱顿大学高级计算机科学研究所）
AlphaZero has achieved impressive performance in deep reinforcement learning by utilizing an architecture that combines search and training of a neural network in self-play. Many researchers are looking for ways to reproduce and improve results for other games/tasks. However, the architecture is designed to learn from scratch, tabula rasa, accepting a cold-start problem in self-play. Recently, a warm-start enhancement method for Monte Carlo Tree Search was proposed to improve the self-play starting phase. It employs a fixed parameter $I^\prime$ to control the warm-start length. Improved perfor…
Hierarchical reinforcement learning has demonstrated significant success at solving difficult reinforcement learning (RL) tasks. Previous works have motivated the use of hierarchy by appealing to a number of intuitive benefits, including learning over temporally extended transitions, exploring over temporally extended periods, and training and exploring in a more semantically meaningful action space, among others. However, in fully observed, Markovian settings, it is not immediately clear why hierarchical RL should provide benefits over standard "shallow" RL architectures. In this work, we iso…
A major challenge in recommender systems is handling new users, whom are also called $\textit{cold-start}$ users. In this paper, we propose a novel approach for learning an optimal series of questions with which to interview cold-start users for movie recommender systems. We propose learning interview questions using Deep Q Networks to create user profiles to make better recommendations to cold-start users. While our proposed system is trained using a movie recommender system, our Deep Q Network model should generalize across various types of recommender systems.
Policy-gradient approaches to reinforcement learning have two common and undesirable overhead procedures, namely warm-start training and sample variance reduction. In this paper, we describe a reinforcement learning method based on a softmax value function that requires neither of these procedures. Our method combines the advantages of policy-gradient methods with the efficiency and simplicity of maximum-likelihood approaches. We apply this new cold-start reinforcement learning method in training sequence generation models for structured output prediction problems. Empirical evidence validates…
We introduce a new generative model for human planning under the Bayesian Inverse Reinforcement Learning (BIRL) framework which takes into account the fact that humans often plan using hierarchical strategies. We describe the Bayesian Inverse Hierarchical RL (BIHRL) algorithm for inferring the values of hierarchical planners, and use an illustrative toy model to show that BIHRL retains accuracy where standard BIRL fails. Furthermore, BIHRL is able to accurately predict the goals of `Wikispeedia' game players, with inclusion of hierarchical structure in the model resulting in a large boost in a…
The Vanguard Group（先锋集团）；University of Toronto（多伦多大学）
Query reformulation aims to alter noisy or ambiguous text sequences into coherent ones closer to natural language questions. This is to prevent errors from propagating in a client-facing pipeline and promote better communication with users. Besides, it is crucial to maintain performance in downstream environments like question answering when rephrased queries are given as input. We show that under the previous framework (AQA), attempts to alter RL algorithms do not bring significant benefits to either reward acquisition or sequence fluency. Instead, we leverage a query-reformulating text-to-te…
Reinforcement Learning (RL) has made remarkable achievements, but it still suffers from inadequate exploration strategies, sparse reward signals, and deceptive reward functions. To alleviate these problems, a Population-guided Novelty Search (PNS) parallel learning method is proposed in this paper. In PNS, the population is divided into multiple sub-populations, each of which has one chief agent and several exploring agents. The chief agent evaluates the policies learned by exploring agents and shares the optimal policy with all sub-populations. The exploring agents learn their policies in col…
New York University Tandon School of Engineering（纽约大学坦登工程学院）；New York University Abu Dhabi（纽约大学阿布扎比分校）
Recent work has shown that the introduction of autonomous vehicles (AVs) in traffic could help reduce traffic jams. Deep reinforcement learning methods demonstrate good performance in complex control problems, including autonomous vehicle control, and have been used in state-of-the-art AV controllers. However, deep neural networks (DNNs) render automated driving vulnerable to machine learning-based attacks. In this work, we explore the backdooring/trojanning of DRL-based AV controllers. We develop a trigger design methodology that is based on well-established principles of traffic physics. The…
Delft University of Technology（代尔夫特理工大学）；TenneT TSO B.V.（TenneT输电系统运营公司）；Smart Wires Inc.（智能电线公司）；RTE（法国输电网络公司）
System operators are faced with increasingly volatile operating conditions. In order to manage system reliability in a cost-effective manner, control room operators are turning to computerised decision support tools based on AI and machine learning. Specifically, Reinforcement Learning (RL) is a promising technique to train agents that suggest grid control actions to operators. In this paper, a simple baseline approach is presented using RL to represent an artificial control room operator that can operate a IEEE 14-bus test case for a duration of 1 week. This agent takes topological switching …
Balancing exploration and exploitation remains a key challenge in reinforcement learning (RL). State-of-the-art RL algorithms suffer from high sample complexity, particularly in the sparse reward case, where they can do no better than to explore in all directions until the first positive rewards are found. To mitigate this, we propose Rapidly Randomly-exploring Reinforcement Learning (R3L). We formulate exploration as a search problem and leverage widely-used planning algorithms such as Rapidly-exploring Random Tree (RRT) to find initial solutions. These solutions are used as demonstrations to…
Reinforcement learning (RL) agents in human-computer interactions applications require repeated user interactions before they can perform well. To address this "cold start" problem, we propose a novel approach of using cognitive models to pre-train RL agents before they are applied to real users. After briefly reviewing relevant cognitive models, we present our general methodological approach, followed by two case studies from our previous and ongoing projects. We hope this position paper stimulates conversations between RL, HCI, and cognitive science researchers in order to explore the full p…
Reinforcement learning (RL) is currently a popular research topic in control engineering and has the potential to make its way to industrial and commercial applications. Corresponding RL controllers are trained in direct interaction with the controlled system, rendering them data-driven and performance-oriented solutions. The best practice of exploring starts (ES) is used by default to support the learning process via randomly picked initial states. However, this method might deliver strongly biased results if the system's dynamic and constraints lead to unfavorable sample distributions in the…
Vrije Universiteit Brussel（布鲁塞尔自由大学）；National University of Ireland Galway（爱尔兰国立大学戈尔韦分校）；University of Antwerp（安特卫普大学）；Hasselt University（哈瑟尔特大学）；HU University of Applied Sciences Utrecht（乌得勒支应用科学大学）
Infectious disease outbreaks can have a disruptive impact on public health and societal processes. As decision making in the context of epidemic mitigation is hard, reinforcement learning provides a methodology to automatically learn prevention strategies in combination with complex epidemic models. Current research focuses on optimizing policies w.r.t. a single objective, such as the pathogen's attack rate. However, as the mitigation of epidemics involves distinct, and possibly conflicting criteria (i.a., prevalence, mortality, morbidity, cost), a multi-objective approach is warranted to lear…
University of Arizona（亚利桑那大学）；Samsung Research America（三星美国研究院）；University of Science and Technology of China（中国科学技术大学）
Reinforcement learning (RL) has shown great promise in optimizing long-term user interest in recommender systems. However, existing RL-based recommendation methods need a large number of interactions for each user to learn a robust recommendation policy. The challenge becomes more critical when recommending to new users who have a limited number of interactions. To that end, in this paper, we address the cold-start challenge in the RL-based recommender systems by proposing a meta-level model-based reinforcement learning approach for fast user adaptation. In our approach, we learn to infer each…
Online reinforcement learning (RL) is increasingly popular for the personalized mobile health (mHealth) intervention. It is able to personalize the type and dose of interventions according to user's ongoing statuses and changing needs. However, at the beginning of online learning, there are usually too few samples to support the RL updating, which leads to poor performances. A delay in good performance of the online learning algorithms can be especially detrimental in the mHealth, where users tend to quickly disengage with the mHealth app. To address this problem, we propose a new online RL me…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Exploration is critical for good results in deep reinforcement learning and has attracted much attention. However, existing multi-agent deep reinforcement learning algorithms still use mostly noise-based techniques. Very recently, exploration methods that consider cooperation among multiple agents have been developed. However, existing methods suffer from a common challenge: agents struggle to identify states that are worth exploring, and hardly coordinate exploration efforts toward those states. To address this shortcoming, in this paper, we propose cooperative multi-agent exploration (CMAE):…
Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）；Nanyang Technological University（南洋理工大学）；Peng Cheng Laboratory（鹏城实验室）
We start with a brief introduction to reinforcement learning (RL), about its successful stories, basics, an example, issues, the ICML 2019 Workshop on RL for Real Life, how to use it, study material and an outlook. Then we discuss a selection of RL applications, including recommender systems, computer systems, energy, finance, healthcare, robotics, and transportation.
Barcelona Neural Networking Center（巴塞罗那神经网络中心）；Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；Institute of Telecommunications（电信研究所）；AGH University of Science and Technology（AGH科技大学）
Deep Reinforcement Learning (DRL) has shown a dramatic improvement in decision-making and automated control problems. Consequently, DRL represents a promising technique to efficiently solve many relevant optimization problems (e.g., routing) in self-driving networks. However, existing DRL-based solutions applied to networking fail to generalize, which means that they are not able to operate properly when applied to network topologies not observed during training. This lack of generalization capability significantly hinders the deployment of DRL technologies in production networks. This is beca…
To Start Up a Start-Up$-$Embedding Strategic Demand Development in Operational On-Demand Fulfillment via Reinforcement Learning with Information Shaping
The University of Tulsa（塔尔萨大学）；Otto von Guericke Universität Magdeburg（马格德堡奥托·冯·格里克大学）；The University of Iowa（爱荷华大学）
We present SafeLife, a publicly available reinforcement learning environment that tests the safety of reinforcement learning agents. It contains complex, dynamic, tunable, procedurally generated levels with many opportunities for unsafe behavior. Agents are graded both on their ability to maximize their explicit reward and on their ability to operate safely without unnecessary side effects. We train agents to maximize rewards using proximal policy optimization and score them on a suite of benchmark levels. The resulting agents are performant but not safe -- they tend to cause large side effect…
