We consider a variant of the traditional multi-armed bandit problem in which each arm is only able to provide one-bit feedback during each pull based on its past history of rewards. Our main result is the following: given an upper confidence bound policy which uses full-reward feedback, there exists a coding scheme for generating one-bit feedback, and a corresponding decoding scheme and arm selection policy, such that the ratio of the regret achieved by our policy and the regret of the full-reward feedback policy asymptotically approaches one.
A key impediment to reinforcement learning (RL) in real applications with limited, batch data is defining a reward function that reflects what we implicitly know about reasonable behaviour for a task and allows for robust off-policy evaluation. In this work, we develop a method to identify an admissible set of reward functions for policies that (a) do not diverge too far from past behaviour, and (b) can be evaluated with high confidence, given only a collection of past trajectories. Together, these ensure that we propose policies that we trust to be implemented in high-risk settings. We demons…
This work explores adaptations of successful multi-armed bandits policies to the online contextual bandits scenario with binary rewards using binary classification algorithms such as logistic regression as black-box oracles. Some of these adaptations are achieved through bootstrapping or approximate bootstrapping, while others rely on other forms of randomness, resulting in more scalable approaches than previous works, and the ability to work with any type of classification algorithm. In particular, the Adaptive-Greedy algorithm shows a lot of promise, in many cases achieving better performanc…
University of Alberta（阿尔伯塔大学）；DeepMind（深度思维）；Google Research（谷歌研究院）
We study high-confidence behavior-agnostic off-policy evaluation in reinforcement learning, where the goal is to estimate a confidence interval on a target policy's value, given only access to a static experience dataset collected by unknown behavior policies. Starting from a function space embedding of the linear program formulation of the $Q$-function, we obtain an optimization problem with generalized estimating equation constraints. By applying the generalized empirical likelihood method to the resulting Lagrangian, we propose CoinDICE, a novel and efficient algorithm for computing confide…
Department of Computer Science（计算机科学系）；University of New Hampshire（新罕布什尔大学）
Robust MDPs (RMDPs) can be used to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution are determined by the ambiguity set---the set of plausible transition probabilities---which is usually constructed as a multi-dimensional confidence region. Existing methods construct ambiguity sets as confidence regions using concentration inequalities which leads to overly conservative solutions. This paper proposes a new paradigm that can achieve better solutions with the same robustness guarantees without using confidence regions …
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Tsinghua University（清华大学）
Off-policy evaluation (OPE) is the task of estimating the expected reward of a given policy based on offline data previously collected under different policies. Therefore, OPE is a key step in applying reinforcement learning to real-world domains such as medical treatment, where interactive data collection is expensive or even unsafe. As the observed data tends to be noisy and limited, it is essential to provide rigorous uncertainty quantification, not just a point estimation, when applying OPE to make high stakes decisions. This work considers the problem of constructing non-asymptotic confid…
Multi-armed bandit problems are considered as a paradigm of the trade-off between exploring the environment to find profitable actions and exploiting what is already known. In the stationary case, the distributions of the rewards do not change in time, Upper-Confidence Bound (UCB) policies have been shown to be rate optimal. A challenging variant of the MABP is the non-stationary bandit problem where the gambler must decide which arm to play while facing the possibility of a changing environment. In this paper, we consider the situation where the distributions of rewards remain constant over e…
Microsoft Dynamics 365 AI（微软 Dynamics 365 人工智能）；Microsoft Research（微软研究院）
We propose an estimator and confidence interval for computing the value of a policy from off-policy data in the contextual bandit setting. To this end we apply empirical likelihood techniques to formulate our estimator and confidence interval as simple convex optimization problems. Using the lower bound of our confidence interval, we then propose an off-policy policy optimization algorithm that searches for policies with large reward lower bound. We empirically find that both our estimator and confidence interval improve over previous proposals in finite sample regimes. Finally, the policy opt…
This study addresses the problem of off-policy evaluation (OPE) from dependent samples obtained via the bandit algorithm. The goal of OPE is to evaluate a new policy using historical data obtained from behavior policies generated by the bandit algorithm. Because the bandit algorithm updates the policy based on past observations, the samples are not independent and identically distributed (i.i.d.). However, several existing methods for OPE do not take this issue into account and are based on the assumption that samples are i.i.d. In this study, we address this problem by constructing an estimat…
Maximising the detection of intrusions is a fundamental and often critical aim of perimeter surveillance. Commonly, this requires a decision-maker to optimally allocate multiple searchers to segments of the perimeter. We consider a scenario where the decision-maker may sequentially update the searchers' allocation, learning from the observed data to improve decisions over time. In this work we propose a formal model and solution methods for this sequential perimeter surveillance problem. Our model is a combinatorial multi-armed bandit (CMAB) with Poisson rewards and a novel filtered feedback m…
Bayesian inverse reinforcement learning (IRL) methods are ideal for safe imitation learning, as they allow a learning agent to reason about reward uncertainty and the safety of a learned policy. However, Bayesian IRL is computationally intractable for high-dimensional problems because each sample from the posterior requires solving an entire Markov Decision Process (MDP). While there exist non-Bayesian deep IRL methods, these methods typically infer point estimates of reward functions, precluding rigorous safety and uncertainty analysis. We propose Bayesian Reward Extrapolation (B-REX), a high…
Yale University（耶鲁大学）；Northwestern University（西北大学）；Mercari, Inc.（Mercari 株式会社）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
Off-policy evaluation (OPE) attempts to predict the performance of counterfactual policies using log data from a different policy. We extend its applicability by developing an OPE method for a class of both full support and deficient support logging policies in contextual-bandit settings. This class includes deterministic bandit (such as Upper Confidence Bound) as well as deterministic decision-making based on supervised and unsupervised learning. We prove that our method's prediction converges in probability to the true performance of a counterfactual policy as the sample size increases. We v…
We study the stochastic multi-armed bandit (MAB) problem in the presence of side-observations across actions that occur as a result of an underlying network structure. In our model, a bipartite graph captures the relationship between actions and a common set of unknowns such that choosing an action reveals observations for the unknowns that it is connected to. This models a common scenario in online social networks where users respond to their friends' activity, thus providing side information about each other's preferences. Our contributions are as follows: 1) We derive an asymptotic lower bo…
Netflix（网飞公司）；Université Paris Descartes（巴黎笛卡尔大学）；Cornell University（康奈尔大学）；University of California, Berkeley（加州大学伯克利分校）
Contextual bandit algorithms are increasingly replacing non-adaptive A/B tests in e-commerce, healthcare, and policymaking because they can both improve outcomes for study participants and increase the chance of identifying good or even best policies. To support credible inference on novel interventions at the end of the study, nonetheless, we still want to construct valid confidence intervals on average treatment effects, subgroup effects, or value of new policies. The adaptive nature of the data collected by contextual bandit algorithms, however, makes this difficult: standard estimators are…
We study the nonstationary stochastic Multi-Armed Bandit (MAB) problem in which the distribution of rewards associated with each arm are assumed to be time-varying and the total variation in the expected rewards is subject to a variation budget. The regret of a policy is defined by the difference in the expected cumulative rewards obtained using the policy and using an oracle that selects the arm with the maximum mean reward at each time. We characterize the performance of the proposed policies in terms of the worst-case regret, which is the supremum of the regret over the set of reward distri…
Technical University of Munich（慕尼黑工业大学）；ETH Zurich（苏黎世联邦理工学院）
Ensuring safety is a crucial challenge when deploying reinforcement learning (RL) to real-world systems. We develop confidence-based safety filters, a control-theoretic approach for certifying state safety constraints for nominal policies learned via standard RL techniques, based on probabilistic dynamics models. Our approach is based on a reformulation of state constraints in terms of cost functions, reducing safety verification to a standard RL task. By exploiting the concept of hallucinating inputs, we extend this formulation to determine a "backup" policy that is safe for the unknown syste…
The Ohio State University（俄亥俄州立大学）；AT&T Labs Research（AT&T实验室研究中心）
We consider stochastic multi-armed bandit problems with graph feedback, where the decision maker is allowed to observe the neighboring actions of the chosen action. We allow the graph structure to vary with time and consider both deterministic and Erdős-Rényi random graph models. For such a graph feedback model, we first present a novel analysis of Thompson sampling that leads to tighter performance bound than existing work. Next, we propose new Information Directed Sampling based policies that are graph-aware in their decision making. Under the deterministic graph case, we establish a Bayesia…
Deep learning has become an increasingly common technique for various control problems, such as robotic arm manipulation, robot navigation, and autonomous vehicles. However, the downside of using deep neural networks to learn control policies is their opaque nature and the difficulties of validating their safety. As the networks used to obtain state-of-the-art results become increasingly deep and complex, the rules they have learned and how they operate become more challenging to understand. This presents an issue, since in safety-critical applications the safety of the control policy must be …
Federal University of Rio Grande do Sul（里约热内卢联邦大学南里奥格兰德分校）；University of Massachusetts（马萨诸塞大学）
Non-stationary environments are challenging for reinforcement learning algorithms. If the state transition and/or reward functions change based on latent factors, the agent is effectively tasked with optimizing a behavior that maximizes performance over a possibly infinite random sequence of Markov Decision Processes (MDPs), each of which drawn from some unknown distribution. We call each such MDP a context. Most related works make strong assumptions such as knowledge about the distribution over contexts, the existence of pre-training phases, or a priori knowledge about the number, sequence, o…
KTH Royal Institute of Technology（瑞典皇家理工学院）；Ericsson Research（爱立信研究院）
Controlling antenna tilts in cellular networks is imperative to reach an efficient trade-off between network coverage and capacity. In this paper, we devise algorithms learning optimal tilt control policies from existing data (in the so-called passive learning setting) or from data actively generated by the algorithms (the active learning setting). We formalize the design of such algorithms as a Best Policy Identification (BPI) problem in Contextual Linear Multi-Arm Bandits (CL-MAB). An arm represents an antenna tilt update; the context captures current network conditions; the reward correspon…
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学）；Peking University（北京大学）
The learned policy of model-free offline reinforcement learning (RL) methods is often constrained to stay within the support of datasets to avoid possible dangerous out-of-distribution actions or states, making it challenging to handle out-of-support region. Model-based RL methods offer a richer dataset and benefit generalization by generating imaginary trajectories with either trained forward or reverse dynamics model. However, the imagined transitions may be inaccurate, thus downgrading the performance of the underlying offline RL method. In this paper, we propose to augment the offline data…
InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees
Shanghai University of Finance and Economics（上海财经大学）；Shanghai Jiao Tong University（上海交通大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Tsinghua University（清华大学）；Boston College（波士顿大学）
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency, which raises a great challenge to find the optimal bitwidth for each layer: it requires domain experts to explore the vast design space trading off among accuracy, latency, energy, and model size, which is both time-consuming and sub-optimal. Conventional quantization algorithm ignores the different hardware architectures and quantizes all the layers in a unifor…
Understanding the impact of the most effective policies or treatments on a response variable of interest is desirable in many empirical works in economics, statistics and other disciplines. Due to the widespread winner's curse phenomenon, conventional statistical inference assuming that the top policies are chosen independent of the random sample may lead to overly optimistic evaluations of the best policies. In recent years, given the increased availability of large datasets, such an issue can be further complicated when researchers include many covariates to estimate the policy or treatment …
A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model
Center for Quantum Computer Science, Faculty of Computing（量子计算机科学中心，计算学院）；University of Latvia（拉脱维亚大学）；HUN-REN Alfréd Rényi Institute of Mathematics（匈牙利-中国阿尔弗雷德·雷尼数学研究所）
We present a Bayesian sequential decision-making formulation of the information filtering problem, in which an algorithm presents items (news articles, scientific papers, tweets) arriving in a stream, and learns relevance from user feedback on presented items. We model user preferences using a Bayesian linear model, similar in spirit to a Bayesian linear bandit. We compute a computational upper bound on the value of the optimal policy, which allows computing an optimality gap for implementable policies. We then use this analysis as motivation in introducing a pair of new Decompose-Then-Decide …
Australian National University（澳大利亚国立大学）；Data61, CSIRO（联邦科学与工业研究组织Data61）；Deakin University（迪肯大学）；Microsoft Research Asia（微软亚洲研究院）
We consider the problem of personalised news recommendation where each user consumes news in a sequential fashion. Existing personalised news recommendation methods focus on exploiting user interests and ignores exploration in recommendation, which leads to biased feedback loops and hurt recommendation quality in the long term. We build on contextual bandits recommendation strategies which naturally address the exploitation-exploration trade-off. The main challenges are the computational efficiency for exploring the large-scale item space and utilising the deep representations with uncertainty…
In this work we present a multi-armed bandit framework for online expert selection in Markov decision processes and demonstrate its use in high-dimensional settings. Our method takes a set of candidate expert policies and switches between them to rapidly identify the best performing expert using a variant of the classical upper confidence bound algorithm, thus ensuring low regret in the overall performance of the system. This is useful in applications where several expert policies may be available, and one needs to be selected at run-time for the underlying environment.
One of the primary challenges in large-scale distributed learning stems from stringent communication constraints. While several recent works address this challenge for static optimization problems, sequential decision-making under uncertainty has remained much less explored in this regard. Motivated by this gap, we introduce a new linear stochastic bandit formulation over a bit-constrained channel. Specifically, in our setup, an agent interacting with an environment transmits encoded estimates of an unknown model parameter to a server over a communication channel of finite capacity. The goal o…
Conventional reinforcement learning methods for Markov decision processes rely on weakly-guided, stochastic searches to drive the learning process. It can therefore be difficult to predict what agent behaviors might emerge. In this paper, we consider an information-theoretic cost function for performing constrained stochastic searches that promote the formation of risk-averse to risk-favoring behaviors. This cost function is the value of information, which provides the optimal trade-off between the expected return of a policy and the policy's complexity; policy complexity is measured by number…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ETH Zürich（苏黎世联邦理工学院）；Imperial College（帝国理工学院）
Simulating the spread of infectious diseases in human communities is critical for predicting the trajectory of an epidemic and verifying various policies to control the devastating impacts of the outbreak. Many existing simulators are based on compartment models that divide people into a few subsets and simulate the dynamics among those subsets using hypothesized differential equations. However, these models lack the requisite granularity to study the effect of intelligent policies that influence every individual in a particular way. In this work, we introduce a simulator software capable of m…
Many sequential decision-making systems leverage data collected using prior policies to propose a new policy. For critical applications, it is important that high-confidence guarantees on the new policy's behavior are provided before deployment, to ensure that the policy will behave as desired. Prior works have studied high-confidence off-policy estimation of the expected return, however, high-confidence off-policy estimation of the variance of returns can be equally critical for high-risk applications. In this paper, we tackle the previously open problem of estimating and bounding, with high …
University of Alberta（阿尔伯塔大学）；Google Research Brain Team（谷歌研究大脑团队）
The presence of uncertainty in policy evaluation significantly complicates the process of policy ranking and selection in real-world settings. We formally consider offline policy selection as learning preferences over a set of policy prospects given a fixed experience dataset. While one can select or rank policies based on point estimates of their policy values or high-confidence intervals, access to the full distribution over one's belief of the policy value enables more flexible selection algorithms under a wider range of downstream evaluation metrics. We propose BayesDICE for estimating thi…
Habana Labs – An Intel company（哈巴纳实验室——英特尔旗下公司）；Department of Electrical Engineering - Technion（以色列理工学院电气工程系）
Neural network quantization methods often involve simulating the quantization process during training, making the trained model highly dependent on the target bit-width and precise way quantization is performed. Robust quantization offers an alternative approach with improved tolerance to different classes of data-types and quantization policies. It opens up new exciting applications where the quantization process is not static and can vary to meet different circumstances and implementations. To address this issue, we propose a method that provides intrinsic robustness to the model against a b…
Oregon State University（俄勒冈州立大学）；Intel Labs（英特尔研究院）
Decision makers often wish to use offline historical data to compare sequential-action policies at various world states. Importantly, computational tools should produce confidence values for such offline policy comparison (OPC) to account for statistical variance and limited data coverage. Nevertheless, there is little work that directly evaluates the quality of confidence values for OPC. In this work, we address this issue by creating benchmarks for OPC with Confidence (OPCC), derived by adding sets of policy comparison queries to datasets from offline reinforcement learning. In addition, we …
In order for an agent to perform well in partially observable domains, it is usually necessary for actions to depend on the history of observations. In this paper, we explore a {\it stigmergic} approach, in which the agent's actions include the ability to set and clear bits in an external memory, and the external memory is included as part of the input to the agent. In this case, we need to learn a reactive policy in a highly non-Markovian domain. We explore two algorithms: SARSA(λ), which has had empirical success in partially observable domains, and VAPS, a new algorithm due to Baird and Moo…
California Institute of Technology（加州理工学院）；Tsinghua University（清华大学）；Carnegie Mellon University（卡内基梅隆大学）
Machine-learned black-box policies are ubiquitous for nonlinear control problems. Meanwhile, crude model information is often available for these problems from, e.g., linear approximations of nonlinear dynamics. We study the problem of equipping a black-box control policy with model-based advice for nonlinear control on a single trajectory. We first show a general negative result that a naive convex combination of a black-box policy and a linear model-based policy can lead to instability, even if the two policies are both stabilizing. We then propose an adaptive $λ$-confident policy, with a co…
Nanjing University（南京大学）；the University of Iowa（爱荷华大学）；Michigan State University（密歇根州立大学）
In this paper, we study a special bandit setting of online stochastic linear optimization, where only one-bit of information is revealed to the learner at each round. This problem has found many applications including online advertisement and online recommendation. We assume the binary feedback is a random variable generated from the logit model, and aim to minimize the regret defined by the unknown linear function. Although the existing method for generalized linear bandit can be applied to our problem, the high computational cost makes it impractical for real-world problems. To address this …
