Designing sample-efficient and computationally feasible reinforcement learning (RL) algorithms is particularly challenging in environments with large or infinite state and action spaces. In this paper, we advance this effort by presenting an efficient algorithm for Markov Decision Processes (MDPs) where the state-action value function of any policy is linear in a given feature map. This challenging setting can model environments with infinite states and actions, strictly generalizes classic linear MDPs, and currently lacks a computationally efficient algorithm under online access to the MDP. Specifically, we introduce a new RL algorithm that efficiently finds a near-optimal policy in this setting, using a number of episodes and calls to a cost-sensitive classification (CSC) oracle that are both polynomial in the problem parameters. Notably, our CSC oracle can be efficiently implemented when the feature dimension is constant, representing a clear improvement over state-of-the-art methods, which require solving non-convex problems with horizon-many variables and can incur computational costs that are exponential in the horizon.
DeepMind；University College London（伦敦大学学院）；University of Illinois（伊利诺伊大学）；University of Alberta（阿尔伯塔大学）
We consider the problem of local planning in fixed-horizon and discounted Markov Decision Processes (MDPs) with linear function approximation and a generative model under the assumption that the optimal action-value function lies in the span of a feature map that is available to the planner. Previous work has left open the question of whether there exist sound planners that need only poly(H,d) queries regardless of the MDP, where H is the horizon and d is the dimensionality of the features. We answer this question in the negative: we show that any sound planner must query at least $\min(\exp(Ω…
We study reinforcement learning in non-episodic factored Markov decision processes (FMDPs). We propose two near-optimal and oracle-efficient algorithms for FMDPs. Assuming oracle access to an FMDP planner, they enjoy a Bayesian and a frequentist regret bound respectively, both of which reduce to the near-optimal bound $\widetilde{O}(DS\sqrt{AT})$ for standard non-factored MDPs. We propose a tighter connectivity measure, factored span, for FMDPs and prove a lower bound that depends on the factored span rather than the diameter $D$. In order to decrease the gap between lower and upper bounds, we…
Princeton University（普林斯顿大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Washington（华盛顿大学）；Microsoft Research（微软研究院）
A fundamental question in the theory of reinforcement learning is: suppose the optimal $Q$-function lies in the linear span of a given $d$ dimensional feature mapping, is sample-efficient reinforcement learning (RL) possible? The recent and remarkable result of Weisz et al. (2020) resolved this question in the negative, providing an exponential (in $d$) sample size lower bound, which holds even if the agent has access to a generative model of the environment. One may hope that this information theoretic barrier for RL can be circumvented by further supposing an even more favorable assumption: …
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…
We study regret minimization in non-episodic factored Markov decision processes (FMDPs), where all existing algorithms make the strong assumption that the factored structure of the FMDP is known to the learner in advance. In this paper, we provide the first algorithm that learns the structure of the FMDP while minimizing the regret. Our algorithm is based on the optimism in face of uncertainty principle, combined with a simple statistical method for structure learning, and can be implemented efficiently given oracle-access to an FMDP planner. Moreover, we give a variant of our algorithm that r…
DeepMind；University College London（伦敦大学学院）；University of Illinois（伊利诺伊大学）；University of Cambridge（剑桥大学）；University of Alberta（阿尔伯塔大学）
We consider local planning in fixed-horizon MDPs with a generative model under the assumption that the optimal value function lies close to the span of a feature map. The generative model provides a local access to the MDP: The planner can ask for random transitions from previously returned states and arbitrary actions, and features are only accessible for states that are encountered in this process. As opposed to previous work (e.g. Lattimore et al. (2020)) where linear realizability of all policies was assumed, we consider the significantly relaxed assumption of a single linearly realizable …
Washington University in St. Louis（圣路易斯华盛顿大学）；University of Southern California（南加州大学）
Many reinforcement learning (RL) environments in practice feature enormous state spaces that may be described compactly by a "factored" structure, that may be modeled by Factored Markov Decision Processes (FMDPs). We present the first polynomial-time algorithm for RL in Factored State MDPs (generalizing FMDPs) that neither relies on an oracle planner nor requires a linear transition model; it only requires a linear value function with a suitable local basis with respect to the factorization, permitting efficient variable elimination. With this assumption, we can solve this family of Factored S…
Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Nanjing University（南京大学）
Q-learning with function approximation could diverge in the off-policy setting and the target network is a powerful technique to address this issue. In this manuscript, we examine the sample complexity of the associated target Q-learning algorithm in the tabular case with a generative oracle. We point out a misleading claim in [Lee and He, 2020] and establish a tight analysis. In particular, we demonstrate that the sample complexity of the target Q-learning algorithm in [Lee and He, 2020] is $\widetilde{\mathcal O}(|\mathcal S|^2|\mathcal A|^2 (1-γ)^{-5}\varepsilon^{-2})$. Furthermore, we show…
Princeton University（普林斯顿大学）；Carnegie Mellon University（卡内基梅隆大学）；Tsinghua University（清华大学）；University of Pennsylvania（宾夕法尼亚大学）
Low-complexity models such as linear function representation play a pivotal role in enabling sample-efficient reinforcement learning (RL). The current paper pertains to a scenario with value-based linear representation, which postulates the linear realizability of the optimal Q-function (also called the "linear $Q^{\star}$ problem"). While linear realizability alone does not allow for sample-efficient solutions in general, the presence of a large sub-optimality gap is a potential game changer, depending on the sampling mechanism in use. Informally, sample efficiency is achievable with a large …
Microsoft Research（微软研究院）；University of Pittsburgh（匹兹堡大学）
We introduce a new programming paradigm called oracle-guided decision programming in which a program specifies a Markov Decision Process (MDP) and the language provides a universal policy. We prototype a new programming language, Dodona, that manifests this paradigm using a primitive 'choose' representing nondeterministic choice. The Dodona interpreter returns either a value or a choicepoint that includes a lossless encoding of all information necessary in principle to make an optimal decision. Meta-interpreters query Dodona's (neural) oracle on these choicepoints to get policy and value estim…
This paper studies the problem of data collection for policy evaluation in Markov decision processes (MDPs). In policy evaluation, we are given a target policy and asked to estimate the expected cumulative reward it will obtain in an environment formalized as an MDP. We develop theory for optimal data collection within the class of tree-structured MDPs by first deriving an oracle data collection strategy that uses knowledge of the variance of the reward distributions. We then introduce the Reduced Variance Sampling (ReVar) algorithm that approximates the oracle strategy when the reward varianc…
University of Alberta（阿尔伯塔大学）；Amii（阿尔伯塔机器智能研究所）；DeepMind
Large-scale Markov decision processes (MDPs) require planning algorithms with runtime independent of the number of states of the MDP. We consider the planning problem in MDPs using linear value function approximation with only weak requirements: low approximation error for the optimal value function, and a small set of "core" states whose features span those of other states. In particular, we make no assumptions about the representability of policies or value functions of non-optimal policies. Our algorithm produces almost-optimal actions for any state using a generative oracle (simulator) for…
University California, Irvine（加州大学欧文分校）；Facebook AI Research (FAIR)（Facebook人工智能研究院）；California institute of technology（加州理工学院）
Reinforcement learning (RL) in Markov decision processes (MDPs) with large state spaces is a challenging problem. The performance of standard RL algorithms degrades drastically with the dimensionality of state space. However, in practice, these large MDPs typically incorporate a latent or hidden low-dimensional structure. In this paper, we study the setting of rich-observation Markov decision processes (ROMDP), where there are a small number of hidden states which possess an injective mapping to the observation states. In other words, every observation state is generated through a single hidde…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Michigan（密歇根大学）
It is a remarkable fact that the same $O(\sqrt{T})$ regret rate can be achieved in both the Experts Problem and the Adversarial Multi-Armed Bandit problem albeit with a worse dependence on number of actions in the latter case. In contrast, it has been shown that handling online MDPs with communicating structure and bandit information incurs $Ω(T^{2/3})$ regret even in the case of deterministic transitions. Is this the price we pay for handling communicating structure or is it because we also have bandit feedback? In this paper we show that with full information, online MDPs can still be learne…
This work studies the question of Representation Learning in RL: how can we learn a compact low-dimensional representation such that on top of the representation we can perform RL procedures such as exploration and exploitation, in a sample efficient manner. We focus on the low-rank Markov Decision Processes (MDPs) where the transition dynamics correspond to a low-rank transition matrix. Unlike prior works that assume the representation is known (e.g., linear MDPs), here we need to learn the representation for the low-rank MDP. We study both the online RL and offline RL settings. For the onlin…
Tel Aviv University（特拉维夫大学）；Google Research（谷歌研究院）
We study learning contextual MDPs using a function approximation for both the rewards and the dynamics. We consider both the case that the dynamics dependent or independent of the context. For both models we derive polynomial sample and time complexity (assuming an efficient ERM oracle). Our methodology gives a general reduction from learning contextual MDP to supervised learning.
Global Convergence of Average Reward Constrained MDPs with Neural Critic and General Policy Parameterization
Department of Computer Science University of Maryland College Park（计算机科学系大学马里兰大学学院公园）；Indian Institute of Technology, Kanpur（印度理工学院坎浦尔）；Department of Electrical Engineering Indian Institute of Technology, Kanpur（电气工程系印度理工学院坎浦尔）；Department of Industrial Engineering Purdue University West Lafayette（工业工程系普渡大学威斯康星拉法叶）
Satisficing Regret Minimization in Bandits: Constant Rate and Light-Tailed Distribution
School of Operations Research and Information Engineering, Cornell University（运营研究与信息工程学院，康奈尔大学）；SC Johnson College of Business, Cornell University（SC约翰逊商学院，康奈尔大学）
N-discount optimality was introduced as a hierarchical form of policy- and value-function optimality, with Blackwell optimality lying at the top level of the hierarchy Veinott (1969); Blackwell (1962). We formalize notions of myopic discount factors, value functions and policies in terms of Blackwell optimality in MDPs, and we provide a novel concept of regret, called Blackwell regret, which measures the regret compared to a Blackwell optimal policy. Our main analysis focuses on long horizon MDPs with sparse rewards. We show that selecting the discount factor under which zero Blackwell regret …
Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs
Department of Statistics, University of Science and Technology of China（统计系，中国科学技术大学）；Department of Epidemiology and Public Health, University of Maryland, Baltimore（流行病学与公共卫生系，马里兰大学巴尔的摩分校）；Department of Technology, Operations, and Statistics, Stern School of Business, New York University（技术、运营与统计系，纽约大学斯特恩商学院）
University of Washington（华盛顿大学）；Carnegie Mellon University（卡内基梅隆大学）
Model-free Reinforcement Learning (RL) algorithms such as Q-learning [Watkins, Dayan 92] have been widely used in practice and can achieve human level performance in applications such as video games [Mnih et al. 15]. Recently, equipped with the idea of optimism in the face of uncertainty, Q-learning algorithms [Jin, Allen-Zhu, Bubeck, Jordan 18] can be proven to be sample efficient for discrete tabular Markov Decision Processes (MDPs) which have finite number of states and actions. In this work, we present an efficient model-free Q-learning based algorithm in MDPs with a natural metric on the …
Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles
University of Maryland（马里兰大学）；U.S. Army Research Laboratory（美国陆军研究实验室）；JP Morgan AI Research（摩根大通人工智能研究院）；Purdue University（普渡大学）；University of Central Florida（中佛罗里达大学）
Tsinghua University（清华大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Florida（佛罗里达大学）
In this paper, we consider the problem of online learning of Markov decision processes (MDPs) with very large state spaces. Under the assumptions of realizable function approximation and low Bellman ranks, we develop an online learning algorithm that learns the optimal value function while at the same time achieving very low cumulative regret during the learning process. Our learning algorithm, Adaptive Value-function Elimination (AVE), is inspired by the policy elimination algorithm proposed in (Jiang et al., 2017), known as OLIVE. One of our key technical contributions in AVE is to formulate…
Tel Aviv University（特拉维夫大学）；Google Research, Tel Aviv（谷歌研究（特拉维夫））
We present regret minimization algorithms for stochastic contextual MDPs under minimum reachability assumption, using an access to an offline least square regression oracle. We analyze three different settings: where the dynamics is known, where the dynamics is unknown but independent of the context and the most challenging setting where the dynamics is unknown and context-dependent. For the latter, our algorithm obtains regret bound of $\widetilde{O}( (H+{1}/{p_{min}})H|S|^{3/2}\sqrt{|A|T\log(\max\{|\mathcal{G}|,|\mathcal{P}|\}/δ)})$ with probability $1-δ$, where $\mathcal{P}$ and $\mathcal{G…
Stanford University（斯坦福大学）；Institute for Computational and Mathematical Engineering（计算与数学工程研究所）
Several practical applications of reinforcement learning involve an agent learning from past data without the possibility of further exploration. Often these applications require us to 1) identify a near optimal policy or to 2) estimate the value of a target policy. For both tasks we derive \emph{exponential} information-theoretic lower bounds in discounted infinite horizon MDPs with a linear function representation for the action value function even if 1) \emph{realizability} holds, 2) the batch algorithm observes the exact reward and transition \emph{functions}, and 3) the batch algorithm is…
Halıcıoğlu Data Science Institute (HDSI), UC San Diego（加州大学圣地亚哥分校哈利奇奥卢数据科学研究所（HDSI））；Boston University（波士顿大学）
We consider model selection for classic Reinforcement Learning (RL) environments -- Multi Armed Bandits (MABs) and Markov Decision Processes (MDPs) -- under general function approximations. In the model selection framework, we do not know the function classes, denoted by $\mathcal{F}$ and $\mathcal{M}$, where the true models -- reward generating function for MABs and and transition kernel for MDPs -- lie, respectively. Instead, we are given $M$ nested function (hypothesis) classes such that true models are contained in at-least one such class. In this paper, we propose and analyze efficient mo…
Reinforcement learning (RL) problems are often phrased in terms of Markov decision processes (MDPs). In this thesis we go beyond MDPs and consider RL in environments that are non-Markovian, non-ergodic and only partially observable. Our focus is not on practical algorithms, but rather on the fundamental underlying problems: How do we balance exploration and exploitation? How do we explore optimally? When is an agent optimal? We follow the nonparametric realizable paradigm. We establish negative results on Bayesian RL agents, in particular AIXI. We show that unlucky or adversarial choices of th…
