我们研究MDP中的强化学习，其转移函数在大多数步骤是随机的，但在每回合固定的$Λ$个步骤子集上可能表现对抗性。该模型捕捉了除少数脆弱点外稳定的环境。我们引入了\emph{条件占用度量}，即使在对抗性转移下也能在回合间保持稳定，并利用它们设计了两种算法。第一种处理任意对抗步骤，实现遗憾$ ilde{O}(H S^Λ\sqrt{K S A^{Λ+1}})$，其中$K$是回合数，$S$是状态数，$A$是动作数，$H$是回合长度。第二种假设对抗步骤连续，将对$S$的依赖改进为$ ilde{O}(H\sqrt{K S^{3} A^{Λ+1}})$。我们进一步给出一个$K^{2/3}$遗憾约简，消除了知道哪些步骤是$Λ$个对抗步骤的需要。我们还刻画了\emph{全对抗}设置（$Λ=H-1$）下对抗性MDP的遗憾，包括完全信息和赌博机反馈，并提供了几乎匹配的上界和下界（略微加强了现有下界，并阐明了不同反馈结构如何影响学习的难度）。
英文摘要：
We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $Λ$ steps per episode. This model captures environments that are stable except at a few vulnerable points. We introduce \emph{conditioned occupancy measures}, which remain stable across episodes even with adversarial transitions, and use them to design two algorithms. The first handles arbitrary adversarial steps and achieves regret $\tilde{O}(H S^Λ\sqrt{K S A^{Λ+1}})$, where $K$ is the number of episodes, $S$ is the number of state, $A$ is the number of actions and $H$ is the episode's horizon. The second, assuming the adversarial steps are consecutive, improves the dependence on $S$ to $\tilde{O}(H\sqrt{K S^{3} A^{Λ+1}})$. We further give a $K^{2/3}$-regret reduction that removes the need to know which steps are the $Λ$ adversarial steps. We also characterize the regret of adversarial MDPs in the \emph{fully adversarial} setting ($Λ=H-1$) both for full-information and bandit feedback, and provide almost matching upper and lower bounds (slightly strengthen existing lower bounds, and clarify how different feedback structures affect the hardness of learning).
Solving Partially Observable Markov Decision Processes (POMDPs) is hard. Learning optimal controllers for POMDPs when the model is unknown is harder. Online learning of optimal controllers for unknown POMDPs, which requires efficient learning using regret-minimizing algorithms that effectively tradeoff exploration and exploitation, is even harder, and no solution exists currently. In this paper, we consider infinite-horizon average-cost POMDPs with unknown transition model, though a known observation model. We propose a natural posterior sampling-based reinforcement learning algorithm (PSRL-PO…
Deep Reinforcement Learning has yielded proficient controllers for complex tasks. However, these controllers have limited memory and rely on being able to perceive the complete game screen at each decision point. To address these shortcomings, this article investigates the effects of adding recurrency to a Deep Q-Network (DQN) by replacing the first post-convolutional fully-connected layer with a recurrent LSTM. The resulting \textit{Deep Recurrent Q-Network} (DRQN), although capable of seeing only a single frame at each timestep, successfully integrates information through time and replicates…
University of Southern California（南加利福尼亚大学）；Tsinghua University（清华大学）
We consider the best-of-both-worlds problem for learning an episodic Markov Decision Process through $T$ episodes, with the goal of achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ regret when the losses are adversarial and simultaneously $\mathcal{O}(\text{polylog}(T))$ regret when the losses are (almost) stochastic. Recent work by [Jin and Luo, 2020] achieves this goal when the fixed transition is known, and leaves the case of unknown transition as a major open question. In this work, we resolve this open problem by using the same Follow-the-Regularized-Leader ($\text{FTRL}$) framework together…
Deep active inference has been proposed as a scalable approach to perception and action that deals with large policy and state spaces. However, current models are limited to fully observable domains. In this paper, we describe a deep active inference model that can learn successful policies directly from high-dimensional sensory inputs. The deep learning architecture optimizes a variant of the expected free energy and encodes the continuous state representation by means of a variational autoencoder. We show, in the OpenAI benchmark, that our approach has comparable or better performance than d…
This work studies the problem of learning episodic Markov Decision Processes with known transition and bandit feedback. We develop the first algorithm with a ``best-of-both-worlds'' guarantee: it achieves $\mathcal{O}(log T)$ regret when the losses are stochastic, and simultaneously enjoys worst-case robustness with $\tilde{\mathcal{O}}(\sqrt{T})$ regret even when the losses are adversarial, where $T$ is the number of episodes. More generally, it achieves $\tilde{\mathcal{O}}(\sqrt{C})$ regret in an intermediate setting where the losses are corrupted by a total amount of $C$. Our algorithm is …
Radboud University（拉德堡德大学）；Nijmegen Institute for Computing and Information Sciences（奈梅亨计算与信息科学研究所）
We study Markov decision processes (MDPs), where agents have direct control over when and how they gather information, as formalized by action-contingent noiselessly observable MDPs (ACNO-MPDs). In these models, actions consist of two components: a control action that affects the environment, and a measurement action that affects what the agent can observe. To solve ACNO-MDPs, we introduce the act-then-measure (ATM) heuristic, which assumes that we can ignore future state uncertainty when choosing control actions. We show how following this heuristic may lead to shorter policy computation time…
Policy optimization is a widely-used method in reinforcement learning. Due to its local-search nature, however, theoretical guarantees on global optimality often rely on extra assumptions on the Markov Decision Processes (MDPs) that bypass the challenge of global exploration. To eliminate the need of such assumptions, in this work, we develop a general solution that adds dilated bonuses to the policy update to facilitate global exploration. To showcase the power and generality of this technique, we apply it to several episodic MDP settings with adversarial losses and bandit feedback, improving…
Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this work, we aim to learn robust MDPs using regularization. We first show that regularized MDPs are a particular instance of robu…
Robust Markov decision processes (MDPs) aim to handle changing or partially known system dynamics. To solve them, one typically resorts to robust optimization methods. However, this significantly increases computational complexity and limits scalability in both learning and planning. On the other hand, regularized MDPs show more stability in policy learning without impairing time complexity. Yet, they generally do not encompass uncertainty in the model dynamics. In this work, we aim to learn robust MDPs using regularization. We first show that regularized MDPs are a particular instance of robu…
Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation
Department of XXX, University of YYY, Location, Country；School of ZZZ, Institute of WWW, Location, Country；Blavatnik School of Computer Science, Tel Aviv University；Google Research；School of Electrical Engineering, Tel Aviv University
Princeton University（普林斯顿大学）；University of Southern California（南加利福尼亚大学）；Massachusetts Institute of Technology（麻省理工学院）
We consider the problem of learning in episodic finite-horizon Markov decision processes with an unknown transition function, bandit feedback, and adversarial losses. We propose an efficient algorithm that achieves $\mathcal{\tilde{O}}(L|X|\sqrt{|A|T})$ regret with high probability, where $L$ is the horizon, $|X|$ is the number of states, $|A|$ is the number of actions, and $T$ is the number of episodes. To the best of our knowledge, our algorithm is the first to ensure $\mathcal{\tilde{O}}(\sqrt{T})$ regret in this challenging setting; in fact it achieves the same regret bound as (Rosenberg &…
Model-free reinforcement learning algorithms combined with value function approximation have recently achieved impressive performance in a variety of application domains. However, the theoretical understanding of such algorithms is limited, and existing results are largely focused on episodic or discounted Markov decision processes (MDPs). In this work, we present adaptive approximate policy iteration (AAPI), a learning scheme which enjoys a $\tilde{O}(T^{2/3})$ regret bound for undiscounted, continuing learning in uniformly ergodic MDPs. This is an improvement over the best existing bound of …
The University of Texas at Austin（得克萨斯大学奥斯汀分校）；Microsoft Research（微软研究院）；Technion（以色列理工学院）；NVIDIA（英伟达）
Learning a near optimal policy in a partially observable system remains an elusive challenge in contemporary reinforcement learning. In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP). There, a reward function is drawn from one of multiple possible reward models at the beginning of every episode, but the identity of the chosen reward model is not revealed to the agent. Hence, the latent state space, for which the dynamics are Markovian, is not given to the agent. We study the problem of learning a near optimal policy for two reward-mixing…
We propose a new, nonparametric approach to estimating the value function in reinforcement learning. This approach makes use of a recently developed representation of conditional distributions as functions in a reproducing kernel Hilbert space. Such representations bypass the need for estimating transition probabilities, and apply to any domain on which kernels can be defined. Our approach avoids the need to approximate intractable integrals since expectations are represented as RKHS inner products whose computation has linear complexity in the sample size. Thus, we can efficiently perform val…
POMDPs are useful models for systems where the true underlying state is not known completely to an outside observer; the outside observer incompletely knows the true state of the system, and observes a noisy version of the true system state. When the number of system states is large in a POMDP that often necessitates the use of approximation methods to obtain near optimal solutions for control. This survey is centered around the origins, theory, and approximations of finite-state POMDPs. In order to understand POMDPs, it is required to have an understanding of finite-state Markov Decision Proc…
City University of Hong Kong（香港城市大学）；University of New Hampshire（新罕布什尔大学）；Imperial College London（帝国理工学院）
Robust Markov decision processes (MDPs) allow to compute reliable solutions for dynamic decision problems whose evolution is modeled by rewards and partially-known transition probabilities. Unfortunately, accounting for uncertainty in the transition probabilities significantly increases the computational complexity of solving robust MDPs, which severely limits their scalability. This paper describes new efficient algorithms for solving the common class of robust MDPs with s- and sa-rectangular ambiguity sets defined by weighted $L_1$ norms. We propose partial policy iteration, a new, efficient…
Unlike traditional reinforcement learning (RL), market-based RL is in principle applicable to worlds described by partially observable Markov Decision Processes (POMDPs), where an agent needs to learn short-term memories of relevant previous events in order to execute optimal actions. Most previous work, however, has focused on reactive settings (MDPs) instead of POMDPs. Here we reimplement a recent approach to market-based RL and for the first time evaluate it in a toy POMDP setting.
Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environments
School of Mechanical Engineering, Yonsei University, Seoul, South Korea（延世大学机械工程学院，首尔，韩国）；Department of Artificial Intelligence, Yonsei University, Seoul, South Korea（延世大学人工智能系，首尔，韩国）；Department of Mechanical Engineering, University of California, Berkeley, United States（加州大学伯克利分校机械工程系，美国）
Missingness-MDPs: Bridging the Theory of Missing Data and POMDPs
Ruhr University Bochum（博德姆鲁尔大学）；Brno University of Technology（布拉格技术大学）；Radboud University Nijmegen（拉德博德大学奈杰姆）；Harvard University（哈佛大学）；Eindhoven University of Technology（埃因霍温理工大学）
We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a model. Our approach is based on the following observation: Any (PO)MDP can be transformed into an "equivalent" POMDP in which all state transitions (given the current state and action) are deterministic. This reduces the general problem of policy search to one in which we need only consider POMDPs with deterministic transitions. We give a natural way of estimating the value of all policies in these transformed POMDPs. P…
DeepMind（深度思维）；Princeton University（普林斯顿大学）；Google Research India（谷歌印度研究院）；University of Alberta（阿尔伯塔大学）
This paper introduces a simple efficient learning algorithms for general sequential decision making. The algorithm combines Optimism for exploration with Maximum Likelihood Estimation for model estimation, which is thus named OMLE. We prove that OMLE learns the near-optimal policies of an enormously rich class of sequential decision making problems in a polynomial number of samples. This rich class includes not only a majority of known tractable model-based Reinforcement Learning (RL) problems (such as tabular MDPs, factored MDPs, low witness rank problems, tabular weakly-revealing/observable …
University of Waterloo（滑铁卢大学）；Monash University（莫纳什大学）
A promising characteristic of Deep Reinforcement Learning (DRL) is its capability to learn optimal policy in an end-to-end manner without relying on feature engineering. However, most approaches assume a fully observable state space, i.e. fully observable Markov Decision Processes (MDPs). In real-world robotics, this assumption is unpractical, because of issues such as sensor sensitivity limitations and sensor noise, and the lack of knowledge about whether the observation design is complete or not. These scenarios lead to Partially Observable MDPs (POMDPs). In this paper, we propose Long-Short…
Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes proposals to learn the learning algorithm itself, an idea also known as meta learning. One formal interpretation of this idea is as a partially observable multi-task RL problem in which task information is hidden from the agent. Such unknown task problems can be reduced to Markov decision processes (MDPs) by augmenting an agent's observations with an estimate of…
Policy optimization methods are popular reinforcement learning algorithms in practice. Recent works have built theoretical foundation for them by proving $\sqrt{T}$ regret bounds even when the losses are adversarial. Such bounds are tight in the worst case but often overly pessimistic. In this work, we show that in tabular Markov decision processes (MDPs), by properly designing the regularizer, the exploration bonus and the learning rates, one can achieve a more favorable polylog$(T)$ regret when the losses are stochastic, without sacrificing the worst-case guarantee in the adversarial regime.…
Graz University of Technology（格拉茨技术大学）；Silicon Austria Labs（奥地利硅实验室）；Lamarr Security Research（拉马尔安全研究院）；Aalborg University（奥尔堡大学）
Safety is still one of the major research challenges in reinforcement learning (RL). In this paper, we address the problem of how to avoid safety violations of RL agents during exploration in probabilistic and partially unknown environments. Our approach combines automata learning for Markov Decision Processes (MDPs) and shield synthesis in an iterative approach. Initially, the MDP representing the environment is unknown. The agent starts exploring the environment and collects traces. From the collected traces, we passively learn MDPs that abstractly represent the safety-relevant aspects of th…
