We consider the problem of batch multi-task reinforcement learning with observed context descriptors, motivated by its application to personalized medical treatment. In particular, we study two general classes of learning algorithms: direct policy learning (DPL), an imitation-learning based approach which learns from expert trajectories, and model-based learning. First, we derive sample complexity bounds for DPL, and then show that model-based learning from expert actions can, even with a finite model class, be impossible. After relaxing the conditions under which the model-based approach is expected to learn by allowing for greater coverage of state-action space, we provide sample complexity bounds for model-based learning with finite model classes, showing that there exist model classes with sample complexity exponential in their statistical complexity. We then derive a sample complexity upper bound for model-based learning based on a measure of concentration of the data distribution. Our results give formal justification for imitation learning over model-based learning in this setting.
New York University Shanghai（上海纽约大学）；New York University（纽约大学）
There has recently been a surge in research in batch Deep Reinforcement Learning (DRL), which aims for learning a high-performing policy from a given dataset without additional interactions with the environment. We propose a new algorithm, Best-Action Imitation Learning (BAIL), which strives for both simplicity and performance. BAIL learns a V function, uses the V function to select actions it believes to be high-performing, and then uses those actions to train a policy network using imitation learning. For the MuJoCo benchmark, we provide a comprehensive experimental study of BAIL, comparing …
Imitation of expert behaviour is a highly desirable and safe approach to the problem of sequential decision making. We provide an easy-to-implement, novel algorithm for imitation learning under a strict data paradigm, in which the agent must learn solely from data collected a priori. This paradigm allows our algorithm to be used for environments in which safety or cost are of critical concern. Our algorithm requires no additional hyper-parameter tuning beyond any standard batch reinforcement learning (RL) algorithm, making it an ideal baseline for such data-strict regimes. Furthermore, we prov…
The options framework for hierarchical reinforcement learning has increased its popularity in recent years and has made improvements in tackling the scalability problem in reinforcement learning. Yet, most of these recent successes are linked with a proper options initialization or discovery. When an expert is available, the options discovery problem can be addressed by learning an options-type hierarchical policy directly from expert demonstrations. This problem is referred to as hierarchical imitation learning and can be handled as an inference problem in a Hidden Markov Model, which is done…
University of Cambridge（剑桥大学）；University of Oxford（牛津大学）；The Alan Turing Institute（艾伦·图灵研究所）；University of California, Los Angeles（加州大学洛杉矶分校）
Consider learning a policy purely on the basis of demonstrated behavior -- that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further interaction with the environment. This *strictly batch imitation learning* problem arises wherever live experimentation is costly, such as in healthcare. One solution is simply to retrofit existing algorithms for apprenticeship learning to work in the offline setting. But such an approach leans heavily on off-policy evaluation or offline model estimation, and can be indirect and inefficient. We argue that a good solutio…
McGill University（麦吉尔大学）；University of Alberta（阿尔伯塔大学）
Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, largely depends on accuracy and correctness of these priors. PAC-Bayesian methods overcome this problem by providing bounds that hold regardless of the correctness of the prior distribution. This paper introduces the first PAC-Bayesian bound for the batch reinforcement learning problem with function approximation. We show how this bound can be used to perform model-selection in a transfer learning scenario. Our empirical …
Recent work by Jarrett et al. attempts to frame the problem of offline imitation learning (IL) as one of learning a joint energy-based model, with the hope of out-performing standard behavioral cloning. We suggest that notational issues obscure how the psuedo-state visitation distribution the authors propose to optimize might be disconnected from the policy's $\textit{true}$ state visitation distribution. We further construct natural examples where the parameter coupling advocated by Jarrett et al. leads to inconsistent estimates of the expert's policy, unlike behavioral cloning.
Koç University（科奇大学）；College of Engineering, Koç University（科奇大学工程学院）
The ability to generate appropriate verbal and non-verbal backchannels by an agent during human-robot interaction greatly enhances the interaction experience. Backchannels are particularly important in applications like tutoring and counseling, which require constant attention and engagement of the user. We present here a method for training a robot for backchannel generation during a human-robot interaction within the reinforcement learning (RL) framework, with the goal of maintaining high engagement level. Since online learning by interaction with a human is highly time-consuming and impract…
Offline Imitation Learning with Model-based Reverse Augmentation
National Key Laboratory for Novel Software Technology（计算机软件新技术国家重点实验室）；Nanjing University（南京大学）；School of Intelligence Science and Technology（智能科学与技术学院）；School of Artificial Intelligence（人工智能学院）
When learning policies for real-world domains, two important questions arise: (i) how to efficiently use pre-collected off-policy, non-optimal behavior data; and (ii) how to mediate among different competing objectives and constraints. We thus study the problem of batch policy learning under multiple constraints, and offer a systematic solution. We first propose a flexible meta-algorithm that admits any batch reinforcement learning and online learning procedure as subroutines. We then present a specific algorithmic instantiation and provide performance guarantees for the main objective and all…
We introduce a novel apprenticeship learning algorithm to learn an expert's underlying reward structure in off-policy model-free \emph{batch} settings. Unlike existing methods that require a dynamics model or additional data acquisition for on-policy evaluation, our algorithm requires only the batch data of observed expert behavior. Such settings are common in real-world tasks---health care, finance or industrial processes ---where accurate simulators do not exist or data acquisition is costly. To address challenges in batch settings, we introduce Deep Successor Feature Networks(DSFN) that est…
Self-driving technology companies and the research community are accelerating their pace to use machine learning longitudinal motion planning (mMP) for autonomous vehicles (AVs). This paper reviews the current state of the art in mMP, with an exclusive focus on its impact on traffic congestion. We identify the availability of congestion scenarios in current datasets, and summarize the required features for training mMP. For learning methods, we survey the major methods in both imitation learning and non-imitation learning. We also highlight the emerging technologies adopted by some leading AV …
University of Oxford（牛津大学）；Microsoft Research（微软研究院）
We present SoftDICE, which achieves state-of-the-art performance for imitation learning. SoftDICE fixes several key problems in ValueDICE, an off-policy distribution matching approach for sample-efficient imitation learning. Specifically, the objective of ValueDICE contains logarithms and exponentials of expectations, for which the mini-batch gradient estimate is always biased. Second, ValueDICE regularizes the objective with replay buffer samples when expert demonstrations are limited in number, which however changes the original distribution matching problem. Third, the re-parametrization tr…
École polytechnique fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Google Research（谷歌研究院）；Hebrew University of Jerusalem (HUJI)（耶路撒冷希伯来大学）；Massachusetts Institute of Technology (MIT)（麻省理工学院）；Toyota Technological Institute at Chicago (TTIC)（芝加哥丰田理工学院）
We study the power of learning via mini-batch stochastic gradient descent (SGD) on the population loss, and batch Gradient Descent (GD) on the empirical loss, of a differentiable model or neural network, and ask what learning problems can be learnt using these paradigms. We show that SGD and GD can always simulate learning with statistical queries (SQ), but their ability to go beyond that depends on the precision $ρ$ of the gradient calculations relative to the minibatch size $b$ (for SGD) and sample size $m$ (for GD). With fine enough precision relative to minibatch size, namely when $b ρ$ is…
Friedrich-Alexander University Erlangen-Nürnberg (FAU)（埃尔朗根-纽伦堡弗里德里希-亚历山大大学（FAU））；Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所（IIS））；Ludwig-Maximilians-University (LMU)（路德维希-马克西米利安大学（LMU））
Active learning (AL) prioritizes the labeling of the most informative data samples. However, the performance of AL heuristics depends on the structure of the underlying classifier model and the data. We propose an imitation learning scheme that imitates the selection of the best expert heuristic at each stage of the AL cycle in a batch-mode pool-based setting. We use DAGGER to train the policy on a dataset and later apply it to datasets from similar domains. With multiple AL heuristics as experts, the policy is able to reflect the choices of the best AL heuristics given the current state of th…
Inria（法国国家信息与自动化研究所）；University College London（伦敦大学学院）
Most PAC-Bayesian bounds hold in the batch learning setting where data is collected at once, prior to inference or prediction. This somewhat departs from many contemporary learning problems where data streams are collected and the algorithms must dynamically adjust. We prove new PAC-Bayesian bounds in this online learning framework, leveraging an updated definition of regret, and we revisit classical PAC-Bayesian results with a batch-to-online conversion, extending their remit to the case of dependent data. Our results hold for bounded losses, potentially \emph{non-convex}, paving the way to p…
Wuhan University（武汉大学）；The University of Sydney（悉尼大学）
Adversarial imitation learning has become a widely used imitation learning framework. The discriminator is often trained by taking expert demonstrations and policy trajectories as examples respectively from two categories (positive vs. negative) and the policy is then expected to produce trajectories that are indistinguishable from the expert demonstrations. But in the real world, the collected expert demonstrations are more likely to be imperfect, where only an unknown fraction of the demonstrations are optimal. Instead of treating imperfect expert demonstrations as absolutely positive or neg…
Control policies from imitation learning can often fail to generalize to novel environments due to imperfect demonstrations or the inability of imitation learning algorithms to accurately infer the expert's policies. In this paper, we present rigorous generalization guarantees for imitation learning by leveraging the Probably Approximately Correct (PAC)-Bayes framework to provide upper bounds on the expected cost of policies in novel environments. We propose a two-stage training method where a latent policy distribution is first embedded with multi-modal expert behavior using a conditional var…
EPFL（洛桑联邦理工学院）；The Alan Turing Institute（阿兰·图灵研究所）；The University of Edinburgh（爱丁堡大学）；University of Cambridge（剑桥大学）
Imitation learning (IL) is a popular paradigm for training policies in robotic systems when specifying the reward function is difficult. However, despite the success of IL algorithms, they impose the somewhat unrealistic requirement that the expert demonstrations must come from the same domain in which a new imitator policy is to be learned. We consider a practical setting, where (i) state-only expert demonstrations from the real (deployment) environment are given to the learner, (ii) the imitation learner policy is trained in a simulation (training) environment whose transition dynamics is sl…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）
Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD): the variance in predicted probability of the correct class across iterations of mini-batch SGD, and the proximity of the correct class probability to the decision threshold. Extensive experimental results on six datasets show that our methods reliably improve accuracy in various network architectures, including additional gains on top of other popular traini…
Courant Institute of Mathematical Sciences（柯朗数学科学研究所）；Google Research（谷歌研究院）
We present a new analysis of the problem of learning with drifting distributions in the batch setting using the notion of discrepancy. We prove learning bounds based on the Rademacher complexity of the hypothesis set and the discrepancy of distributions both for a drifting PAC scenario and a tracking scenario. Our bounds are always tighter and in some cases substantially improve upon previous ones based on the $L_1$ distance. We also present a generalization of the standard on-line to batch conversion to the drifting scenario in terms of the discrepancy and arbitrary convex combinations of hyp…
Understanding the source of the superior generalization ability of NNs remains one of the most important problems in ML research. There have been a series of theoretical works trying to derive non-vacuous bounds for NNs. Recently, the compression of information stored in weights (IIW) is proved to play a key role in NNs generalization based on the PAC-Bayes theorem. However, no solution of IIW has ever been provided, which builds a barrier for further investigation of the IIW's property and its potential in practical deep learning. In this paper, we propose an algorithm for the efficient appro…
