Most reinforcement learning methods are based upon the key assumption that the transition dynamics and reward functions are fixed, that is, the underlying Markov decision process is stationary. However, in many real-world applications, this assumption is violated, and using existing algorithms may result in a performance lag. To proactively search for a good future policy, we present a policy gradient algorithm that maximizes a forecast of future performance. This forecast is obtained by fitting a curve to the counter-factual estimates of policy performance over time, without explicitly modeling the underlying non-stationarity. The resulting algorithm amounts to a non-uniform reweighting of past data, and we observe that minimizing performance over some of the data from past episodes can be beneficial when searching for a policy that maximizes future performance. We show that our algorithm, called Prognosticator, is more robust to non-stationarity than two online adaptation techniques, on three simulated problems motivated by real-world applications.
In this paper, we propose new problem-independent lower bounds on the sample complexity and regret in episodic MDPs, with a particular focus on the non-stationary case in which the transition kernel is allowed to change in each stage of the episode. Our main contribution is a novel lower bound of $Ω((H^3SA/ε^2)\log(1/δ))$ on the sample complexity of an $(\varepsilon,δ)$-PAC algorithm for best policy identification in a non-stationary MDP. This lower bound relies on a construction of "hard MDPs" which is different from the ones previously used in the literature. Using this same class of MDPs, w…
A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent problems. We study an episodic setting where the parameters of an MDP can differ across episodes. We learn a reliable policy of this potentially adversarial MDP by developing an Adversarial Reinforcement Learning (ARL) algorithm that reduces our MDP to a sequence of \emph{adversarial} bandit problems. ARL achieves $O(\sqrt{SATH^3})$ regret, which is optimal with re…
University of New Hampshire（新罕布什尔大学）；City University of Hong Kong（香港城市大学）
We address the problem of computing reliable policies in reinforcement learning problems with limited data. In particular, we compute policies that achieve good returns with high confidence when deployed. This objective, known as the \emph{percentile criterion}, can be optimized using Robust MDPs~(RMDPs). RMDPs generalize MDPs to allow for uncertain transition probabilities chosen adversarially from given ambiguity sets. We show that the RMDP solution's sub-optimality depends on the spans of the ambiguity sets along the value function. We then propose new algorithms that minimize the span of a…
Optimal policies in Markov decision processes (MDPs) are very sensitive to model misspecification. This raises serious concerns about deploying them in high-stake domains. Robust MDPs (RMDP) provide a promising framework to mitigate vulnerabilities by computing policies with worst-case guarantees in reinforcement learning. The solution quality of an RMDP depends on the ambiguity set, which is a quantification of model uncertainties. In this paper, we propose a new approach for optimizing the shape of the ambiguity sets for RMDPs. Our method departs from the conventional idea of constructing a …
Université de Toulouse（图卢兹大学）；ONERA - The French Aerospace Lab（法国航空航天实验室（ONERA））；ISAE-SUPAERO（法国高等航空航天学院）
This work tackles the problem of robust zero-shot planning in non-stationary stochastic environments. We study Markov Decision Processes (MDPs) evolving over time and consider Model-Based Reinforcement Learning algorithms in this setting. We make two hypotheses: 1) the environment evolves continuously with a bounded evolution rate; 2) a current model is known at each decision epoch but not its evolution. Our contribution can be presented in four points. 1) we define a specific class of MDPs that we call Non-Stationary MDPs (NSMDPs). We introduce the notion of regular evolution by making an hyp…
University of Massachusetts（马萨诸塞大学）；Adobe Research（奥多比研究院）；University of Alberta（阿尔伯塔大学）；Amii（Amii（阿尔伯塔机器智能研究所））
Many real-world sequential decision-making problems involve critical systems with financial risks and human-life risks. While several works in the past have proposed methods that are safe for deployment, they assume that the underlying problem is stationary. However, many real-world problems of interest exhibit non-stationarity, and when stakes are high, the cost associated with a false stationarity assumption may be unacceptable. We take the first steps towards ensuring safety, with high confidence, for smoothly-varying non-stationary decision problems. Our proposed method extends a type of s…
Robustness is important for sequential decision making in a stochastic dynamic environment with uncertain probabilistic parameters. We address the problem of using robust MDPs (RMDPs) to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution is determined by its ambiguity set. Existing methods construct ambiguity sets that lead to impractically conservative solutions. In this paper, we propose RSVF, which achieves less conservative solutions with the same worst-case guarantees by 1) leveraging a Bayesian prior, 2) optimizi…
Recently, we have struck the balance between the information freshness, in terms of age of information (AoI), experienced by users and energy consumed by sensors, by appropriately activating sensors to update their current status in caching enabled Internet of Things (IoT) networks [1]. To solve this problem, we cast the corresponding status update procedure as a continuing Markov Decision Process (MDP) (i.e., without termination states), where the number of state-action pairs increases exponentially with respect to the number of considered sensors and users. Moreover, to circumvent the curse …
We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under drifting non-stationarity, i.e., both the reward and state transition distributions are allowed to evolve over time, as long as their respective total variations, quantified by suitable metrics, do not exceed certain variation budgets. We first develop the Sliding Window Upper-Confidence bound for Reinforcement Learning with Confidence Widening (SWUCRL2-CW) algorithm, and establish its dynamic regret bound when the variation budgets are known. In addition, we propose the Bandit-over-Reinforcement Le…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Sandia National Laboratories（桑迪亚国家实验室）
We consider Markov Decision Processes (MDPs) in which every stationary policy induces the same graph structure for the underlying Markov chain and further, the graph has the following property: if we replace each recurrent class by a node, then the resulting graph is acyclic. For such MDPs, we prove the convergence of the stochastic dynamics associated with a version of optimistic policy iteration (OPI), suggested in Tsitsiklis (2002), in which the values associated with all the nodes visited during each iteration of the OPI are updated.
We propose a black-box reduction that turns a certain reinforcement learning algorithm with optimal regret in a (near-)stationary environment into another algorithm with optimal dynamic regret in a non-stationary environment, importantly without any prior knowledge on the degree of non-stationarity. By plugging different algorithms into our black-box, we provide a list of examples showing that our approach not only recovers recent results for (contextual) multi-armed bandits achieved by very specialized algorithms, but also significantly improves the state of the art for (generalized) linear b…
DeepMind（深度思维）；University College London（伦敦大学学院）；University of Alberta（阿尔伯塔大学）；Omron Sinic X（欧姆龙Sinic X）
We consider approximate dynamic programming in $γ$-discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first contribution is a new variant of Approximate Policy Iteration (API), called Confident Approximate Policy Iteration (CAPI), which computes a deterministic stationary policy with an optimal error bound scaling linearly with the product of the effective horizon $H$ and the worst-case approximation error $ε$ of the action-value functions of stationary policies. This improvement over API (whose error scales with $H^2$) comes…
National University of Singapore（新加坡国立大学）；Massachusetts Institute of Technology（麻省理工学院）
We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under temporal drifts, ie, both the reward and state transition distributions are allowed to evolve over time, as long as their respective total variations, quantified by suitable metrics, do not exceed certain variation budgets. This setting captures the endogeneity, exogeneity, uncertainty, and partial feedback in sequential decision-making scenarios, and finds applications in vehicle remarketing and real-time bidding. We first develop the Sliding Window Upper-Confidence bound for Reinforcement Learning…
Dynamic optimization of mean and variance in Markov decision processes (MDPs) is a long-standing challenge caused by the failure of dynamic programming. In this paper, we propose a new approach to find the globally optimal policy for combined metrics of steady-state mean and variance in an infinite-horizon undiscounted MDP. By introducing the concepts of pseudo mean and pseudo variance, we convert the original problem to a bilevel MDP problem, where the inner one is a standard MDP optimizing pseudo mean-variance and the outer one is a single parameter selection problem optimizing pseudo mean. …
This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs). For MDPs that are ergodic and linear (i.e. where rewards and dynamics are linear in some known features), we provide the first finite-sample OPE error bound, extending existing results beyond the episodic and discounted cases. In a more general setting, when the feature dynamics are approximately linear and for arbitrary rewards, we propose a new approach for estimating stationary distributions with function approximation. We formulate this problem as …
We consider a Reinforcement Learning setup where an agent interacts with an environment in observation-reward-action cycles without any (esp.\ MDP) assumptions on the environment. State aggregation and more generally feature reinforcement learning is concerned with mapping histories/raw-states to reduced/aggregated states. The idea behind both is that the resulting reduced process (approximately) forms a small stationary finite-state MDP, which can then be efficiently solved or learnt. We considerably generalize existing aggregation results by showing that even if the reduced process is not an…
Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
Computer Science and Automation, Indian Institute of Science, Bengaluru（印度科学研究院计算机科学与自动化部门，班加罗尔）；Computer Science and Engineering, Indian Institute of Technology Madras, Chennai（印度理工学院马德拉斯分校计算机科学与工程系，钦奈）；Tata Consultancy Services Limited, Hyderabad（海得拉巴市塔塔咨询公司）
UC Santa Barbara（加州大学圣巴巴拉分校）；Salesforce Research（Salesforce研究院）
We consider the problem of offline reinforcement learning (RL) -- a well-motivated setting of RL that aims at policy optimization using only historical data. Despite its wide applicability, theoretical understandings of offline RL, such as its optimal sample complexity, remain largely open even in basic settings such as \emph{tabular} Markov Decision Processes (MDPs). In this paper, we propose Off-Policy Double Variance Reduction (OPDVR), a new variance reduction based algorithm for offline RL. Our main result shows that OPDVR provably identifies an $ε$-optimal policy with $\widetilde{O}(H^2/d…
Inria Lille（里尔法国国家信息与自动化研究所）；Université de Lille（里尔大学）；OvGU（马格德堡大学）；Facebook AI Research（脸书人工智能研究院）；CNRS（法国国家科学研究中心）；DeepMind Paris（深度思维巴黎）
In this work, we propose KeRNS: an algorithm for episodic reinforcement learning in non-stationary Markov Decision Processes (MDPs) whose state-action set is endowed with a metric. Using a non-parametric model of the MDP built with time-dependent kernels, we prove a regret bound that scales with the covering dimension of the state-action space and the total variation of the MDP with time, which quantifies its level of non-stationarity. Our method generalizes previous approaches based on sliding windows and exponential discounting used to handle changing environments. We further propose a pract…
University of Edinburgh（爱丁堡大学）；Imperial College London（帝国理工学院）；Vega Protocol（维加协议）；The Alan Turing Institute（艾伦·图灵研究所）
We study the global convergence of policy gradient for infinite-horizon, continuous state and action space, and entropy-regularized Markov decision processes (MDPs). We consider a softmax policy with (one-hidden layer) neural network approximation in a mean-field regime. Additional entropic regularization in the associated mean-field probability measure is added, and the corresponding gradient flow is studied in the 2-Wasserstein metric. We show that the objective function is increasing along the gradient flow. Further, we prove that if the regularization in terms of the mean-field measure is …
Efficient Algorithms for Robust Markov Decision Processes with $s$-Rectangular Ambiguity Sets
Department of Data Science, City University of Hong Kong（香港城市大学数据科学系）；Department of Computer Science, University of New Hampshire（新罕布什尔大学计算机科学系）；Imperial College Business School, Imperial College London（伦敦帝国理工学院商学院）
Mila, Université de Montréal（蒙特利尔大学Mila研究所）；Facebook AI Research（Facebook人工智能研究院）
We study episodic reinforcement learning in non-stationary linear (a.k.a. low-rank) Markov Decision Processes (MDPs), i.e, both the reward and transition kernel are linear with respect to a given feature map and are allowed to evolve either slowly or abruptly over time. For this problem setting, we propose OPT-WLSVI an optimistic model-free algorithm based on weighted least squares value iteration which uses exponential weights to smoothly forget data that are far in the past. We show that our algorithm, when competing against the best policy at each time, achieves a regret that is upper bound…
INRIA Lille - Nord Europe（法国国立信息学及其应用研究院里尔-北欧中心）；Adobe Research（奥多比研究院）；INRIA Lille（法国国立信息学及其应用研究院里尔中心）
In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in rewards in addition to maximizing a standard criterion. Variance related risk measures are among the most common risk-sensitive criteria in finance and operations research. However, optimizing many such criteria is known to be a hard problem. In this paper, we consider both discounted and average reward Markov decision processes. For each formulation, we first define a measure of variability for a policy, which in turn gives us a set of risk-sensitive criteria to optimize. For ea…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）
Planning provides a framework for optimizing sequential decisions in complex environments. Recent advances in efficient planning in deterministic or stochastic high-dimensional domains with continuous action spaces leverage backpropagation through a model of the environment to directly optimize actions. However, existing methods typically not take risk into account when optimizing in stochastic domains, which can be incorporated efficiently in MDPs by optimizing the entropic utility of returns. We bridge this gap by introducing Risk-Aware Planning using PyTorch (RAPTOR), a novel framework for …
Politecnico di Milano（米兰理工大学）；Inria（法国国家信息与自动化研究所）
In this paper, we propose a novel reinforcement- learning algorithm consisting in a stochastic variance-reduced version of policy gradient for solving Markov Decision Processes (MDPs). Stochastic variance-reduced gradient (SVRG) methods have proven to be very successful in supervised learning. However, their adaptation to policy gradient is not straightforward and needs to account for I) a non-concave objective func- tion; II) approximations in the full gradient com- putation; and III) a non-stationary sampling pro- cess. The result is SVRPG, a stochastic variance- reduced policy gradient algo…
University of Central Florida（中佛罗里达大学）；Air Force Research Laboratory（空军研究实验室）
The planning domain has experienced increased interest in the formal synthesis of decision-making policies. This formal synthesis typically entails finding a policy which satisfies formal specifications in the form of some well-defined logic. While many such logics have been proposed with varying degrees of expressiveness and complexity in their capacity to capture desirable agent behavior, their value is limited when deriving decision-making policies which satisfy certain types of asymptotic behavior in general system models. In particular, we are interested in specifying constraints on the s…
Optimizing Electric Bus Charging Scheduling with Uncertainties Using Hierarchical Deep Reinforcement Learning
School of Engineering, University of Guelph（圭尔夫大学工程学院）；EthicalAI（伦理AI）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）
In this paper, we revisit the regret of undiscounted reinforcement learning in MDPs with a birth and death structure. Specifically, we consider a controlled queue with impatient jobs and the main objective is to optimize a trade-off between energy consumption and user-perceived performance. Within this setting, the \emph{diameter} $D$ of the MDP is $Ω(S^S)$, where $S$ is the number of states. Therefore, the existing lower and upper bounds on the regret at time$T$, of order $O(\sqrt{DSAT})$ for MDPs with $S$ states and $A$ actions, may suggest that reinforcement learning is inefficient here. In…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Cornell University（康奈尔大学）
Monte-Carlo planning, as exemplified by Monte-Carlo Tree Search (MCTS), has demonstrated remarkable performance in applications with finite spaces. In this paper, we consider Monte-Carlo planning in an environment with continuous state-action spaces, a much less understood problem with important applications in control and robotics. We introduce POLY-HOOT, an algorithm that augments MCTS with a continuous armed bandit strategy named Hierarchical Optimistic Optimization (HOO) (Bubeck et al., 2011). Specifically, we enhance HOO by using an appropriate polynomial, rather than logarithmic, bonus t…
