We study reinforcement learning (RL) in high dimensional episodic Markov decision processes (MDP). We consider value-based RL when the optimal Q-value is a linear function of d-dimensional state-action feature representation. For instance, in deep-Q networks (DQN), the Q-value is a linear function of the feature representation layer (output layer). We propose two algorithms, one based on optimism, LINUCB, and another based on posterior sampling, LINPSRL. We guarantee frequentist and Bayesian regret upper bounds of O(d sqrt{T}) for these two algorithms, where T is the number of episodes. We extend these methods to deep RL and propose Bayesian deep Q-networks (BDQN), which uses an efficient Thompson sampling algorithm for high dimensional RL. We deploy the double DQN (DDQN) approach, and instead of learning the last layer of Q-network using linear regression, we use Bayesian linear regression, resulting in an approximated posterior over Q-function. This allows us to directly incorporate the uncertainty over the Q-function and deploy Thompson sampling on the learned posterior distribution resulting in efficient exploration/exploitation trade-off. We empirically study the behavior of BDQN on a wide range of Atari games. Since BDQN carries out more efficient exploration and exploitation, it is able to reach higher return substantially faster compared to DDQN.
Optimism about the poorly understood states and actions is the main driving force of exploration for many provably-efficient reinforcement learning algorithms. We propose optimism in the face of sensible value functions (OFVF)- a novel data-driven Bayesian algorithm to constructing Plausibility sets for MDPs to explore robustly minimizing the worst case exploration cost. The method computes policies with tighter optimistic estimates for exploration by introducing two new ideas. First, it is based on Bayesian posterior distributions rather than distribution-free bounds. Second, OFVF does not co…
To maximize its success, an AGI typically needs to explore its initially unknown world. Is there an optimal way of doing so? Here we derive an affirmative answer for a broad class of environments.
The human intrinsic desire to pursue knowledge, also known as curiosity, is considered essential in the process of skill acquisition. With the aid of artificial curiosity, we could equip current techniques for control, such as Reinforcement Learning, with more natural exploration capabilities. A promising approach in this respect has consisted of using Bayesian surprise on model parameters, i.e. a metric for the difference between prior and posterior beliefs, to favour exploration. In this contribution, we propose to apply Bayesian surprise in a latent space representing the agent's current un…
University of Cambridge（剑桥大学）；Alan Turing Institute（艾伦·图灵研究所）；University College London（伦敦大学学院）
The use of ensembles of neural networks (NNs) for the quantification of predictive uncertainty is widespread. However, the current justification is intuitive rather than analytical. This work proposes one minor modification to the normal ensembling methodology, which we prove allows the ensemble to perform Bayesian inference, hence converging to the corresponding Gaussian Process as both the total number of NNs, and the size of each, tend to infinity. This working paper provides early-stage results in a reinforcement learning setting, analysing the practicality of the technique for an ensemble…
Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, where optimality improves with increased computational time. This is because the resulting planning task takes the form of a dynamic programming problem on a belief tree with an infinite number of states. The second type employs relatively simple algorithm which are shown to suffer small regret within a distribution-free framework. This paper presents a lower bound and a high probability upper bound on the optimal valu…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Università degli Studi di Milano（米兰大学）；Université Laval（拉瓦尔大学）；University of Leoben（莱奥本大学）；University College London（伦敦大学学院）
We develop a coherent framework for integrative simultaneous analysis of the exploration-exploitation and model order selection trade-offs. We improve over our preceding results on the same subject (Seldin et al., 2011) by combining PAC-Bayesian analysis with Bernstein-type inequality for martingales. Such a combination is also of independent interest for studies of multiple simultaneously evolving martingales.
We consider Bayesian optimization of expensive-to-evaluate experiments that generate vector-valued outcomes over which a decision-maker (DM) has preferences. These preferences are encoded by a utility function that is not known in closed form but can be estimated by asking the DM to express preferences over pairs of outcome vectors. To address this problem, we develop Bayesian optimization with preference exploration, a novel framework that alternates between interactive real-time preference learning with the DM via pairwise comparisons between outcomes, and Bayesian optimization with a learne…
Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms. In this paper, we focus on model-free RL using the epsilon-greedy exploration policy, which despite its simplicity, remains one of the most frequently used forms of exploration. However, a key limitation of this policy is the specification of $\varepsilon$. In this paper, we provide a novel Bayesian perspective of $\varepsilon$ as a measure of the uniformity of the Q-value function. We introduce a closed-form Bayesian model update based on B…
Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $ε$-greedy. This contributes to the problem of high sample complexity, as the algorithm wastes effort by repeatedly visiting parts of the state space that have already been explored. We introduce a novel method based on Bayesian linear regression and latent space embedding to generate an intrinsic reward signal that encourages the learning agent to seek out unexplored parts of the state space. This method is computationally efficient…
Turn Inc（Turn公司）；Microsoft Inc（微软公司）；Oregon State University（俄勒冈州立大学）
The problem of optimizing unknown costly-to-evaluate functions has been studied for a long time in the context of Bayesian Optimization. Algorithms in this field aim to find the optimizer of the function by asking only a few function evaluations at locations carefully selected based on a posterior model. In this paper, we assume the unknown function is Lipschitz continuous. Leveraging the Lipschitz property, we propose an algorithm with a distinct exploration phase followed by an exploitation phase. The exploration phase aims to select samples that shrink the search space as much as possible. …
University of British Columbia（不列颠哥伦比亚大学）；Hebrew University（希伯来大学）；University of California（加利福尼亚大学）
Reinforcement learning systems are often concerned with balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of exploration can be estimated using the classical notion of Value of Information - the expected improvement in future decision quality arising from the information acquired by exploration. Estimating this quantity requires an assessment of the agent's uncertainty about its current value estimates for states. In this paper we investigate ways of representing and reasoning about this uncertainty in algorithms where the system a…
Non-negative Matrix Factorization (NMF) is a popular tool for data exploration. Bayesian NMF promises to also characterize uncertainty in the factorization. Unfortunately, current inference approaches such as MCMC mix slowly and tend to get stuck on single modes. We introduce a novel approach using rapidly-exploring random trees (RRTs) to asymptotically cover regions of high posterior density. These are placed in a principled Bayesian framework via an online extension to nonparametric variational inference. On experiments on real and synthetic data, we obtain greater coverage of the posterior …
Massachusetts Institute of Technology, Lincoln Laboratory（麻省理工学院林肯实验室）
Multiple techniques for producing calibrated predictive probabilities using deep neural networks in supervised learning settings have emerged that leverage approaches to ensemble diverse solutions discovered during cyclic training or training from multiple random starting points (deep ensembles). However, only a limited amount of work has investigated the utility of exploring the local region around each diverse solution (posterior mode). Using three well-known deep architectures on the CIFAR-10 dataset, we evaluate several simple methods for exploring local regions of the weight space with re…
We propose a framework based on distributional reinforcement learning and recent attempts to combine Bayesian parameter updates with deep reinforcement learning. We show that our proposed framework conceptually unifies multiple previous methods in exploration. We also derive a practical algorithm that achieves efficient exploration on challenging control tasks.
Sorbonne Université（索邦大学）；INSERM（法国国家健康与医学研究院）；CNRS（法国国家科学研究中心）；Institut de la Vision（视觉研究所）
Bayesian optimization (BO) is an effective approach to optimize expensive black-box functions, that seeks to trade-off between exploitation (selecting parameters where the maximum is likely) and exploration (selecting parameters where we are uncertain about the objective function). In many real-world situations, direct measurements of the objective function are not possible, and only binary measurements such as success/failure or pairwise comparisons are available. To perform efficient exploration in this setting, we show that it is important for BO algorithms to distinguish between different …
We propose a model-based lifelong reinforcement-learning approach that estimates a hierarchical Bayesian posterior distilling the common structure shared across different tasks. The learned posterior combined with a sample-based Bayesian exploration procedure increases the sample efficiency of learning across a family of related tasks. We first derive an analysis of the relationship between the sample complexity and the initialization quality of the posterior in the finite MDP setting. We next scale the approach to continuous-state domains by introducing a Variational Bayesian Lifelong Reinfor…
Bayesian optimization (BO) and its batch extensions are successful for optimizing expensive black-box functions. However, these traditional BO approaches are not yet ideal for optimizing less expensive functions when the computational cost of BO can dominate the cost of evaluating the blackbox function. Examples of these less expensive functions are cheap machine learning models, inexpensive physical experiment through simulators, and acquisition function optimization in Bayesian optimization. In this paper, we consider a batch BO setting for situations where function evaluations are less expe…
Northeastern University（东北大学）；Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室（MERL））
Learning data representations that capture task-related features, but are invariant to nuisance variations remains a key challenge in machine learning. We introduce an automated Bayesian inference framework, called AutoBayes, that explores different graphical models linking classifier, encoder, decoder, estimator and adversarial network blocks to optimize nuisance-invariant machine learning pipelines. AutoBayes also enables learning disentangled representations, where the latent variable is split into multiple pieces to impose various relationships with the nuisance variation and task labels. …
Chalmers University of Technology（查尔姆斯理工大学）；ENS（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；PSL University（巴黎文理研究大学）；Inria（法国国家信息与自动化研究所）；National University of Singapore（新加坡国立大学）
We propose a generic, Bayesian, information geometric approach to the exploration--exploitation trade-off in multi-armed bandit problems. Our approach, BelMan, uniformly supports pure exploration, exploration--exploitation, and two-phase bandit problems. The knowledge on bandit arms and their reward distributions is summarised by the barycentre of the joint distributions of beliefs and rewards of the arms, the \emph{pseudobelief-reward}, within the beliefs-rewards manifold. BelMan alternates \emph{information projection} and \emph{reverse information projection}, i.e., projection of the pseudo…
École Polytechnique（巴黎综合理工学院）；University of Oslo（奥斯陆大学）；Athens University of Economics and Business（雅典经济与商业大学）
We introduce Bayesian least-squares policy iteration (BLSPI), an off-policy, model-free, policy iteration algorithm that uses the Bayesian least-squares temporal-difference (BLSTD) learning algorithm to evaluate policies. An online variant of BLSPI has been also proposed, called randomised BLSPI (RBLSPI), that improves its policy based on an incomplete policy evaluation step. In online setting, the exploration-exploitation dilemma should be addressed as we try to discover the optimal policy by using samples collected by ourselves. RBLSPI exploits the advantage of BLSTD to quantify our uncertai…
Reinforcement learning studies how to balance exploration and exploitation in real-world systems, optimizing interactions with the world while simultaneously learning how the world operates. One general class of algorithms for such learning is the multi-armed bandit setting. Randomized probability matching, based upon the Thompson sampling approach introduced in the 1930s, has recently been shown to perform well and to enjoy provable optimality properties. It permits generative, interpretable modeling in a Bayesian setting, where prior knowledge is incorporated, and the computed posteriors nat…
UCB Exploration for Fixed-Budget Bayesian Best Arm Identification
Institute of Science and Technology for Brain-inspired Intelligence, Fudan University（复旦大学脑科学智能技术研究院）；School of Mathematics and Statistics, Wuhan University（武汉大学数学与统计学院）
Stanford University（斯坦福大学）；University of Toronto（多伦多大学）；Vector Institute（矢量研究所）
The exploration mechanism used by a Deep Reinforcement Learning (RL) agent plays a key role in determining its sample efficiency. Thus, improving over random exploration is crucial to solve long-horizon tasks with sparse rewards. We propose to leverage an ensemble of partial solutions as teachers that guide the agent's exploration with action suggestions throughout training. While the setup of learning with teachers has been previously studied, our proposed approach - Actor-Critic with Teacher Ensembles (AC-Teach) - is the first to work with an ensemble of suboptimal teachers that may solve on…
Rutgers University（罗格斯大学）；Massachusetts Institute of Technology（麻省理工学院）
We present a modular approach to reinforcement learning that uses a Bayesian representation of the uncertainty over models. The approach, BOSS (Best of Sampled Set), drives exploration by sampling multiple models from the posterior and selecting actions optimistically. It extends previous work by providing a rule for deciding when to resample and how to combine the models. We show that our algorithm achieves nearoptimal reward with high probability with a sample complexity that is low relative to the speed at which the posterior distribution converges during learning. We demonstrate that BOSS …
University of California（加利福尼亚大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
In this article we explore an alternative approach to address deep exploration and we introduce the ISL algorithm, which is efficient at performing deep exploration. Similarly to maximum entropy RL, we derive the algorithm by augmenting the traditional RL objective with a novel regularization term. A distinctive feature of our approach is that, as opposed to other works that tackle the problem of deep exploration, in our derivation both the learning equations and the exploration-exploitation strategy are derived in tandem as the solution to a well-posed optimization problem whose minimization …
Within the framework of probably approximately correct Markov decision processes (PAC-MDP), much theoretical work has focused on methods to attain near optimality after a relatively long period of learning and exploration. However, practical concerns require the attainment of satisfactory behavior within a short period of time. In this paper, we relax the PAC-MDP conditions to reconcile theoretically driven exploration methods and practical needs. We propose simple algorithms for discrete and continuous state spaces, and illustrate the benefits of our proposed relaxation via theoretical analys…
Brigham Young University（杨百翰大学）；Harvard University（哈佛大学）
This paper introduces a probabilistic framework to estimate parameters of an acquisition function given observed human behavior that can be modeled as a collection of sample paths from a Bayesian optimization procedure. The methodology involves defining a likelihood on observed human behavior from an optimization task, where the likelihood is parameterized by a Bayesian optimization subroutine governed by an unknown acquisition function. This structure enables us to make inference on a subject's acquisition function while allowing their behavior to deviate around the solution to the Bayesian o…
Bayesian optimization offers the possibility of optimizing black-box operations not accessible through traditional techniques. The success of Bayesian optimization methods such as Expected Improvement (EI) are significantly affected by the degree of trade-off between exploration and exploitation. Too much exploration can lead to inefficient optimization protocols, whilst too much exploitation leaves the protocol open to strong initial biases, and a high chance of getting stuck in a local minimum. Typically, a constant margin is used to control this trade-off, which results in yet another hyper…
Bayesian Optimization by Kernel Regression and Density-based Exploration
Zhiyuan College, Shanghai Jiao Tong University, Shanghai 200240, P. R. China（上海交通大学紫阳学院）；School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai 200240, P. R. China（上海交通大学数学科学学院）；Shanghai Institute of Aerospace Systems Engineering, Shanghai 201109, P. R. China（上海航天系统工程研究院）；Department of Mathematics, Shanghai University, Shanghai 200444, P. R. China（上海大学数学系）；Newtouch Center for Mathematics of Shanghai University, Shanghai University, Shanghai 200444, P. R. China（上海大学数学中心）
One of the main challenges of deep learning tools is their inability to capture model uncertainty. While Bayesian deep learning can be used to tackle the problem, Bayesian neural networks often require more time and computational power to train than deterministic networks. Our work explores whether fully Bayesian networks are needed to successfully capture model uncertainty. We vary the number and position of Bayesian layers in a network and compare their performance on active learning with the MNIST dataset. We found that we can fully capture the model uncertainty by using only a few Bayesian…
Implementing Bayesian variable selection for linear Gaussian regression models for analysing high dimensional data sets is of current interest in many fields. In order to make such analysis operational, we propose a new sampling algorithm based upon Evolutionary Monte Carlo and designed to work under the "large p, small n" paradigm, thus making fully Bayesian multivariate analysis feasible, for example, in genetics/genomics experiments. Two real data examples in genomics are presented, demonstrating the performance of the algorithm in a space of up to 10,000 covariates. Finally the methodology…
Microsoft Research（微软研究院）；University of Pennsylvania（宾夕法尼亚大学）；University of Minnesota（明尼苏达大学）
It is common in recommendation systems that users both consume and produce information as they make strategic choices under uncertainty. While a social planner would balance "exploration" and "exploitation" using a multi-armed bandit algorithm, users' incentives may tilt this balance in favor of exploitation. We consider Bayesian Exploration: a simple model in which the recommendation system (the "principal") controls the information flow to the users (the "agents") and strives to incentivize exploration via information asymmetry. A single round of this model is a version of a well-known "Baye…
We train a reinforcement learner to play a simplified version of the game Angry Birds. The learner is provided with a game state in a manner similar to the output that could be produced by computer vision algorithms. We improve on the efficiency of regular ε-greedy Q-Learning with linear function approximation through more systematic exploration in Randomized Least Squares Value Iteration (RLSVI), an algorithm that samples its policy from a posterior distribution on optimal policies. With larger state-action spaces, efficient exploration becomes increasingly important, as evidenced by the fast…
We study the use of randomized value functions to guide deep exploration in reinforcement learning. This offers an elegant means for synthesizing statistically and computationally efficient exploration with common practical approaches to value function learning. We present several reinforcement learning algorithms that leverage randomized value functions and demonstrate their efficacy through computational studies. We also prove a regret bound that establishes statistical efficiency with a tabular representation.
Deep ensembles can be considered as the current state-of-the-art for uncertainty quantification in deep learning. While the approach was originally proposed as a non-Bayesian technique, arguments supporting its Bayesian footing have been put forward as well. We show that deep ensembles can be viewed as an approximate Bayesian method by specifying the corresponding assumptions. Our findings lead to an improved approximation which results in an enlarged epistemic part of the uncertainty. Numerical examples suggest that the improved approximation can lead to more reliable uncertainties. Analytica…
University of Exeter（埃克塞特大学）；Swansea University（斯旺西大学）
The performance of acquisition functions for Bayesian optimisation to locate the global optimum of continuous functions is investigated in terms of the Pareto front between exploration and exploitation. We show that Expected Improvement (EI) and the Upper Confidence Bound (UCB) always select solutions to be expensively evaluated on the Pareto front, but Probability of Improvement is not guaranteed to do so and Weighted Expected Improvement does so only for a restricted range of weights. We introduce two novel $ε$-greedy acquisition functions. Extensive empirical evaluation of these together wi…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not suitable for system identification in the multi-task setting. We present a novel method to facilitate exploration in multi-task reinforcement learning using deep generative models. We supplement our method with a low dimensional energy model to learn the underlying MDP distribution and provide a resilient and adaptive exploration signal to the agent. We eva…
The problem of inverse reinforcement learning (IRL) is relevant to a variety of tasks including value alignment and robot learning from demonstration. Despite significant algorithmic contributions in recent years, IRL remains an ill-posed problem at its core; multiple reward functions coincide with the observed behavior and the actual reward function is not identifiable without prior knowledge or supplementary information. This paper presents an IRL framework called Bayesian optimization-IRL (BO-IRL) which identifies multiple solutions that are consistent with the expert demonstrations by effi…
Recent advances in deep reinforcement learning have made significant strides in performance on applications such as Go and Atari games. However, developing practical methods to balance exploration and exploitation in complex domains remains largely unsolved. Thompson Sampling and its extension to reinforcement learning provide an elegant approach to exploration that only requires access to posterior samples of the model. At the same time, advances in approximate Bayesian methods have made posterior approximation for flexible neural network models practical. Thus, it is attractive to consider a…
Imperial College London（伦敦帝国理工学院）；ETH Zurich（苏黎世联邦理工学院）
Efficient exploration remains a major challenge for reinforcement learning. One reason is that the variability of the returns often depends on the current state and action, and is therefore heteroscedastic. Classical exploration strategies such as upper confidence bound algorithms and Thompson sampling fail to appropriately account for heteroscedasticity, even in the bandit setting. Motivated by recent findings that address this issue in bandits, we propose to use Information-Directed Sampling (IDS) for exploration in reinforcement learning. As our main contribution, we build on recent advance…
University of Guelph（圭尔夫大学）；Vector Institute for AI（Vector人工智能研究所）；Google（谷歌）
Neural bandits have been shown to provide an efficient solution to practical sequential decision tasks that have nonlinear reward functions. The main contributor to that success is approximate Bayesian inference, which enables neural network (NN) training with uncertainty estimates. However, Bayesian NNs often suffer from a prohibitive computational overhead or operate on a subset of parameters. Alternatively, certain classes of infinite neural networks were shown to directly correspond to Gaussian processes (GP) with neural kernels (NK). NK-GPs provide accurate uncertainty estimates and can b…
Designing efficient exploration is central to Reinforcement Learning due to the fundamental problem posed by the exploration-exploitation dilemma. Bayesian exploration strategies like Thompson Sampling resolve this trade-off in a principled way by modeling and updating the distribution of the parameters of the action-value function, the outcome model of the environment. However, this technique becomes infeasible for complex environments due to the computational intractability of maintaining probability distributions over parameters of outcome models of corresponding complexity. Moreover, the a…
University of California, San Diego（加利福尼亚大学圣迭戈分校）；Twitter（推特公司）
Recommender systems trained in a continuous learning fashion are plagued by the feedback loop problem, also known as algorithmic bias. This causes a newly trained model to act greedily and favor items that have already been engaged by users. This behavior is particularly harmful in personalised ads recommendations, as it can also cause new campaigns to remain unexplored. Exploration aims to address this limitation by providing new information about the environment, which encompasses user preference, and can lead to higher long-term reward. In this work, we formulate a display advertising recom…
