University of Oxford（牛津大学）；University of British Columbia（不列颠哥伦比亚大学）；Inverted AI（Inverted AI公司）；Alberta Machine Learning Intelligence Institute (AMII)（阿尔伯塔机器学习智能研究所（AMII））；Montréal Institute for Learning Algorithms (MILA)（蒙特利尔学习算法研究所（MILA））
Andrew Warrington, J. Wilder Lavington, Adam Ścibior, Mark Schmidt, Frank Wood
Policies for partially observed Markov decision processes can be efficiently learned by imitating policies for the corresponding fully observed Markov decision processes. Unfortunately, existing approaches for this kind of imitation learning have a serious flaw: the expert does not know what the trainee cannot see, and so may encourage actions that are sub-optimal, even unsafe, under partial information. We derive an objective to instead train the expert to maximize the expected reward of the imitating agent policy, and use it to construct an efficient algorithm, adaptive asymmetric DAgger (A2D), that jointly trains the expert and the agent. We show that A2D produces an expert policy that the agent can safely imitate, in turn outperforming policies learned by imitating a fixed expert.
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
In real-world scenarios, the observation data for reinforcement learning with continuous control is commonly noisy and part of it may be dynamically missing over time, which violates the assumption of many current methods developed for this. We addressed the issue within the framework of partially observable Markov Decision Process (POMDP) using a model-based method, in which the transition model is estimated from the incomplete and noisy observations using a newly proposed surrogate loss function with local approximation, while the policy and value function is learned with the help of belief …
UIUC（伊利诺伊大学厄巴纳-香槟分校）；Uber AI Labs（优步人工智能实验室）；UT Austin（德克萨斯大学奥斯汀分校）
We consider the problem of imitation learning from expert demonstrations in partially observable Markov decision processes (POMDPs). Belief representations, which characterize the distribution over the latent states in a POMDP, have been modeled using recurrent neural networks and probabilistic latent variable models, and shown to be effective for reinforcement learning in POMDPs. In this work, we investigate the belief representation learning problem for generative adversarial imitation learning in POMDPs. Instead of training the belief module and the policy separately as suggested in prior w…
ETH Zürich（苏黎世联邦理工学院）；Swiss Federal Railways SBB（瑞士联邦铁路）；Technical University of Munich（慕尼黑工业大学）；Pennsylvania State Univ.（宾夕法尼亚州立大学）
Structural Health Monitoring (SHM) describes a process for inferring quantifiable metrics of structural condition, which can serve as input to support decisions on the operation and maintenance of infrastructure assets. Given the long lifespan of critical structures, this problem can be cast as a sequential decision making problem over prescribed horizons. Partially Observable Markov Decision Processes (POMDPs) offer a formal framework to solve the underlying optimal planning task. However, two issues can undermine the POMDP solutions. Firstly, the need for a model that can adequately describe…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Radboud University（拉德堡德大学）；University of California, Berkeley（加州大学伯克利分校）；Eindhoven University of Technology（埃因霍温理工大学）
Uncertain partially observable Markov decision processes (uPOMDPs) allow the probabilistic transition and observation functions of standard POMDPs to belong to a so-called uncertainty set. Such uncertainty, referred to as epistemic uncertainty, captures uncountable sets of probability distributions caused by, for instance, a lack of data available. We develop an algorithm to compute finite-memory policies for uPOMDPs that robustly satisfy specifications against any admissible distribution. In general, computing such policies is theoretically and practically intractable. We provide an efficient…
The Partially Observable Markov Decision Process (POMDP) is a powerful framework for capturing decision-making problems that involve state and transition uncertainty. However, most current POMDP planners cannot effectively handle high-dimensional image observations prevalent in real world applications, and often require lengthy online training that requires interaction with the environment. In this work, we propose Visual Tree Search (VTS), a compositional learning and planning procedure that combines generative models learned offline with online model-based POMDP planning. The deep generative…
In many practical settings control decisions must be made under partial/imperfect information about the evolution of a relevant state variable. Partially Observable Markov Decision Processes (POMDPs) is a relatively well-developed framework for modeling and analyzing such problems. In this paper we consider the structural estimation of the primitives of a POMDP model based upon the observable history of the process. We analyze the structural properties of POMDP model with random rewards and specify conditions under which the model is identifiable without knowledge of the state dynamics. We con…
Université de Montréal（蒙特利尔大学）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）；Carnegie Mellon University（卡内基梅隆大学）
Many problems in RL, such as meta-RL, robust RL, generalization in RL, and temporal credit assignment, can be cast as POMDPs. In theory, simply augmenting model-free RL with memory-based architectures, such as recurrent neural networks, provides a general approach to solving all types of POMDPs. However, prior work has found that such recurrent model-free RL methods tend to perform worse than more specialized algorithms that are designed for specific types of POMDPs. This paper revisits this claim. We find that careful architecture and hyperparameter decisions can often yield a recurrent model…
ODE-based Recurrent Model-free Reinforcement Learning for POMDPs
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Rutgers University（罗格斯大学）；Electronics and Telecommunications Research Institute（电子与电信研究所）；Rutgers Center for Cognitive Science（罗格斯认知科学中心）
Object-centric world models provide structured representation of the scene and can be an important backbone in reinforcement learning and planning. However, existing approaches suffer in partially-observable environments due to the lack of belief states. In this paper, we propose Structured World Belief, a model for learning and inference of object-centric belief states. Inferred by Sequential Monte Carlo (SMC), our belief states provide multiple object-centric scene hypotheses. To synergize the benefits of SMC particles with object representations, we also propose a new object-centric dynamic…
London School of Economics and Political Science（伦敦政治经济学院）；Cornell University（康奈尔大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes (POMDPs), where the evaluation policy depends only on observable variables and the behavior policy depends on unobservable latent variables. Existing works either assume no unmeasured confounders, or focus on settings where both the observation and the state spaces are tabular. In this work, we first propose novel identification methods for OPE in POMDPs with latent confounders, by introducing bridge functions that link the target policy's value and the observed data distribution. We next propose minimax …
Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）
Robust Belief-State Policy Learning for Quantum Network Routing Under Decoherence and Time-Varying Conditions
Department of Electrical Engineering, Columbia University（哥伦比亚大学电气工程系）；Department of Electrical Engineering, Imam Khomeini International University（伊玛目·霍梅尼国际大学电气工程系）；Department of Electrical Engineering, Qatar University（卡塔尔大学电气工程系）
This paper presents an algorithmic framework for learning robust policies in asymmetric imperfect-information games, where the joint reward could depend on the uncertain opponent type (a private information known only to the opponent itself and its ally). In order to maximize the reward, the protagonist agent has to infer the opponent type through agent modeling. We use multiagent reinforcement learning (MARL) to learn opponent models through self-play, which captures the full strategy interaction and reasoning between agents. However, agent policies learned from self-play can suffer from mutu…
Active Bayesian Inference for Robust Control under Sensor False Data Injection Attacks
Department of Network and Systems Engineering, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology（瑞典皇家理工学院电气工程与计算机科学学院网络与系统工程系）
We consider classification in the presence of class-dependent asymmetric label noise with unknown noise probabilities. In this setting, identifiability conditions are known, but additional assumptions were shown to be required for finite sample rates, and so far only the parametric rate has been obtained. Assuming these identifiability conditions, together with a measure-smoothness condition on the regression function and Tsybakov's margin condition, we show that the Robust kNN classifier of Gao et al. attains, the minimax optimal rates of the noise-free setting, up to a log factor, even when …
Xi’an Jiaotong University（西安交通大学）；Xi’an Microelectronic Technology Institute（西安微电子技术研究所）；Harbin Engineering University（哈尔滨工程大学）；National Space Science Center, Chinese Academy of Sciences（中国科学院国家空间科学中心）
In recent years, correntropy has been seccessfully applied to robust adaptive filtering to eliminate adverse effects of impulsive noises or outliers. Correntropy is generally defined as the expectation of a Gaussian kernel between two random variables. This definition is reasonable when the error between the two random variables is symmetrically distributed around zero. For the case of asymmetric error distribution, the symmetric Gaussian kernel is however inappropriate and cannot adapt to the error distribution well. To address this problem, in this brief we propose a new variant of correntro…
Virginia Tech（弗吉尼亚理工大学）；Kuwait University（科威特大学）；Department of Industrial and Systems Engineering, Virginia Tech（弗吉尼亚理工大学工业与系统工程系）；Department of Industrial and Management Systems Engineering, Kuwait University（科威特大学工业与管理系统工程系）
Some response surface functions in complex engineering systems are usually highly nonlinear, unformed, and expensive-to-evaluate. To tackle this challenge, Bayesian optimization, which conducts sequential design via a posterior distribution over the objective function, is a critical method used to find the global optimum of black-box functions. Kernel functions play an important role in shaping the posterior distribution of the estimated function. The widely used kernel function, e.g., radial basis function (RBF), is very vulnerable and susceptible to outliers; the existence of outliers is cau…
Beyond Fixed Points: Superpolynomial Capacity of Asymmetric Hopfield Networks
COATI, CNRS, Inria, I3S, Université Côte d’Azur, France（法国国家科学研究中心（CNRS）、法国国家信息与自动化研究所（Inria）、I3S研究所、蔚蓝海岸大学）；School of Electrical and Computer Engineering, Tel Aviv University, Israel（特拉维夫大学电气与计算机工程学院）；Department of Informatics, King’s College London, UK（伦敦国王学院信息学院）；Institute of Science and Technology Austria (ISTA), Klosterneuburg, Austria（奥地利科学与技术研究所（ISTA））
Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE
School of Information and Software Engineering, University of Electronic Science and Technology of China（信息与软件工程学院，电子科学与技术大学）；School of Computer Science and Engineering, Central South University（计算机科学与工程学院，中南大学）
Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Tsinghua University（清华大学）
Robust loss functions are essential for training deep neural networks with better generalization power in the presence of noisy labels. Symmetric loss functions are confirmed to be robust to label noise. However, the symmetric condition is overly restrictive. In this work, we propose a new class of loss functions, namely \textit{asymmetric loss functions}, which are robust to learning with noisy labels for various types of noise. We investigate general theoretical properties of asymmetric loss functions, including classification calibration, excess risk bound, and noise tolerance. Meanwhile, w…
Institut Louis Bachelier（路易·巴舍利耶研究所）；Société Générale（法国兴业银行）
The growing popularity of Graph Representation Learning (GRL) methods has resulted in the development of a large number of models applied to a miscellany of domains. Behind this diversity of domains, there is a strong heterogeneity of graphs, making it difficult to estimate the expected performance of a model on a new graph, especially when the graph has distinctive characteristics that have not been encountered in the benchmark yet. To address this, we have developed an experimental pipeline, to assess the impact of a given property on the models performances. In this paper, we use this pipel…
Graph clustering problems typically aim to partition the graph nodes such that two nodes belong to the same partition set if and only if they are similar. Correlation Clustering is a graph clustering formulation which: (1) takes as input a signed graph with edge weights representing a similarity/dissimilarity measure between the nodes, and (2) requires no prior estimate of the number of clusters in the input graph. However, the combinatorial optimization problem underlying Correlation Clustering is NP-hard. In this work, we propose a novel graph generative model, called the Node Factors Model …
