While multitask representation learning has become a popular approach in reinforcement learning (RL), theoretical understanding of why and when it works remains limited. This paper presents analyses for the statistical benefit of multitask representation learning in linear Markov Decision Process (MDP) under a generative model. In this paper, we consider an agent to learn a representation function $ϕ$ out of a function class $Φ$ from $T$ source tasks with $N$ data per task, and then use the learned $\hatϕ$ to reduce the required number of sample for a new task. We first discover a \emph{Least-Activated-Feature-Abundance} (LAFA) criterion, denoted as $κ$, with which we prove that a straightforward least-square algorithm learns a policy which is $\tilde{O}(H^2\sqrt{\frac{\mathcal{C}(Φ)^2 κd}{NT}+\frac{κd}{n}})$ sub-optimal. Here $H$ is the planning horizon, $\mathcal{C}(Φ)$ is $Φ$'s complexity measure, $d$ is the dimension of the representation (usually $d\ll \mathcal{C}(Φ)$) and $n$ is the number of samples for the new task. Thus the required $n$ is $O(κd H^4)$ for the sub-optimality to be close to zero, which is much smaller than $O(\mathcal{C}(Φ)^2κd H^4)$ in the setting without multitask representation learning, whose sub-optimality gap is $\tilde{O}(H^2\sqrt{\frac{κ\mathcal{C}(Φ)^2d}{n}})$. This theoretically explains the power of multitask representation learning in reducing sample complexity. Further, we note that to ensure high sample efficiency, the LAFA criterion $κ$ should be small. In fact, $κ$ varies widely in magnitude depending on the different sampling distribution for new task. This indicates adaptive sampling technique is important to make $κ$ solely depend on $d$. Finally, we provide empirical results of a noisy grid-world environment to corroborate our theoretical findings.
Tsinghua University（清华大学）；University of Washington（华盛顿大学）
While multitask representation learning has become a popular approach in reinforcement learning (RL) to boost the sample efficiency, the theoretical understanding of why and how it works is still limited. Most previous analytical works could only assume that the representation function is already known to the agent or from linear function class, since analyzing general function class representation encounters non-trivial technical obstacles such as generalization guarantee, formulation of confidence bound in abstract function space, etc. However, linear-case analysis heavily relies on the part…
University of Science and Technology of China（中国科学技术大学）；The Pennsylvania State University（宾夕法尼亚州立大学）；The Ohio State University（俄亥俄州立大学）
As representation learning becomes a powerful technique to reduce sample complexity in reinforcement learning (RL) in practice, theoretical understanding of its advantage is still limited. In this paper, we theoretically characterize the benefit of representation learning under the low-rank Markov decision process (MDP) model. We first study multitask low-rank RL (as upstream training), where all tasks share a common representation, and propose a new multitask reward-free algorithm called REFUEL. REFUEL learns both the transition kernel and the near-optimal policy for each task, and outputs a …
KAIST（韩国科学技术院）；King’s College London（伦敦国王学院）；Naver Corporation（Naver公司）
We consider the Markov Decision Process (MDP) of selecting a subset of items at each step, termed the Select-MDP (S-MDP). The large state and action spaces of S-MDPs make them intractable to solve with typical reinforcement learning (RL) algorithms especially when the number of items is huge. In this paper, we present a deep RL algorithm to solve this issue by adopting the following key ideas. First, we convert the original S-MDP into an Iterative Select-MDP (IS-MDP), which is equivalent to the S-MDP in terms of optimal actions. IS-MDP decomposes a joint action of selecting K items simultaneou…
Universidad Carlos III de Madrid（卡洛斯三世大学）；J. P. Morgan AI Research（摩根大通人工智能研究院）
Markov Decision Processes (MDPs) are an effective way to formally describe many Machine Learning problems. In fact, recently MDPs have also emerged as a powerful framework to model financial trading tasks. For example, financial MDPs can model different market scenarios. However, the learning of a (near-)optimal policy for each of these financial MDPs can be a very time-consuming process, especially when nothing is known about the policy to begin with. An alternative approach is to find a similar financial MDP for which we have already learned its policy, and then reuse such policy in the lear…
VTT Technical Research Centre of Finland（芬兰VTT技术研究中心）；University of Electro-Communications（电气通信大学）；Zhejiang University（浙江大学）；University of Oslo（奥斯陆大学）；University of Oulu（奥卢大学）
This paper targets at the problem of radio resource management for expected long-term delay-power tradeoff in vehicular communications. At each decision epoch, the road side unit observes the global network state, allocates channels and schedules data packets for all vehicle user equipment-pairs (VUE-pairs). The decision-making procedure is modelled as a discrete-time Markov decision process (MDP). The technical challenges in solving an optimal control policy originate from highly spatial mobility of vehicles and temporal variations in data traffic. To simplify the decision-making process, we …
Tsinghua University（清华大学）；University of Washington（华盛顿大学）
This paper gives the first polynomial-time algorithm for tabular Markov Decision Processes (MDP) that enjoys a regret bound \emph{independent on the planning horizon}. Specifically, we consider tabular MDP with $S$ states, $A$ actions, a planning horizon $H$, total reward bounded by $1$, and the agent plays for $K$ episodes. We design an algorithm that achieves an $O\left(\mathrm{poly}(S,A,\log K)\sqrt{K}\right)$ regret in contrast to existing bounds which either has an additional $\mathrm{polylog}(H)$ dependency~\citep{zhang2020reinforcement} or has an exponential dependency on $S$~\citep{li2…
LLM2TEA: An Agentic AI Designer for Discovery with Generative Evolutionary Multitasking
1 College of Computing \& Data Science (CCDS), Nanyang Technological University (NTU), Singapore 2 Honda Research Institute Europe (HRI-EU), Offenbach am Main, Germany 3 Centre for Frontier AI Research (CFAR), Agency for Science, Technology
Learning Markov decision processes (MDPs) in the presence of the adversary is a challenging problem in reinforcement learning (RL). In this paper, we study RL in episodic MDPs with adversarial reward and full information feedback, where the unknown transition probability function is a linear function of a given feature mapping, and the reward function can change arbitrarily episode by episode. We propose an optimistic policy optimization algorithm POWERS and show that it can achieve $\tilde{O}(dH\sqrt{T})$ regret, where $H$ is the length of the episode, $T$ is the number of interactions with t…
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…
Evaluations of Deep Reinforcement Learning (DRL) methods are an integral part of scientific progress of the field. Beyond designing DRL methods for general intelligence, designing task-specific methods is becoming increasingly prominent for real-world applications. In these settings, the standard evaluation practice involves using a few instances of Markov Decision Processes (MDPs) to represent the task. However, many tasks induce a large family of MDPs owing to variations in the underlying environment, particularly in real-world contexts. For example, in traffic signal control, variations may…
Technische Universität Darmstadt（达姆施塔特工业大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Tampere University（坦佩雷大学）
We consider Monte-Carlo Tree Search (MCTS) applied to Markov Decision Processes (MDPs) and Partially Observable MDPs (POMDPs), and the well-known Upper Confidence bound for Trees (UCT) algorithm. In UCT, a tree with nodes (states) and edges (actions) is incrementally built by the expansion of nodes, and the values of nodes are updated through a backup strategy based on the average value of child nodes. However, it has been shown that with enough samples the maximum operator yields more accurate node value estimates than averaging. Instead of settling for one of these value estimates, we go a s…
Federated Learning With Energy Harvesting Devices: An MDP Framework
Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology（香港科技大学电子与计算机工程系）；School of Electrical Engineering and Computer Science, Washington State University（华盛顿州立大学电气与计算机科学学院）
Google Inc.（谷歌公司）；University of Washington（华盛顿大学）；University of Kentucky（肯塔基大学）
Value iteration is a powerful yet inefficient algorithm for Markov decision processes (MDPs) because it puts the majority of its effort into backing up the entire state space, which turns out to be unnecessary in many cases. In order to overcome this problem, many approaches have been proposed. Among them, ILAO* and variants of RTDP are state-of-the-art ones. These methods use reachability analysis and heuristic search to avoid some unnecessary backups. However, none of these approaches build the graphical structure of the state transitions in a pre-processing step or use the structural inform…
Real-Time and Embedded Computing Systems Research Centre（实时与嵌入式计算系统研究中心）；Commonwealth Scientific and Industrial Research Organization（联邦科学与工业研究组织）
Unmanned Aerial Vehicles (UAVs) with Microwave Power Transfer (MPT) capability provide a practical means to deploy a large number of wireless powered sensing devices into areas with no access to persistent power supplies. The UAV can charge the sensing devices remotely and harvest their data. A key challenge is online MPT and data collection in the presence of on-board control of a UAV (e.g., patrolling velocity) for preventing battery drainage and data queue overflow of the sensing devices, while up-to-date knowledge on battery level and data queue of the devices is not available at the UAV. …
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…
University of Michigan（密歇根大学）；Northwestern University（西北大学）；Princeton University（普林斯顿大学）
To achieve sample efficiency in reinforcement learning (RL), it necessitates efficiently exploring the underlying environment. Under the offline setting, addressing the exploration challenge lies in collecting an offline dataset with sufficient coverage. Motivated by such a challenge, we study the reward-free RL problem, where an agent aims to thoroughly explore the environment without any pre-specified reward function. Then, given any extrinsic reward, the agent computes the policy via a planning algorithm with offline data collected in the exploration phase. Moreover, we tackle this problem …
We consider the problem of power allocation over a time-varying channel with unknown distribution in energy harvesting communication systems. In this problem, the transmitter has to choose the transmit power based on the amount of stored energy in its battery with the goal of maximizing the average rate obtained over time. We model this problem as a Markov decision process (MDP) with the transmitter as the agent, the battery status as the state, the transmit power as the action and the rate obtained as the reward. The average reward maximization problem over the MDP can be solved by a linear p…
Budapest University of Technology and Economics（布达佩斯技术与经济大学）
An in-depth understanding of the particular environment is crucial in reinforcement learning (RL). To address this challenge, the decision-making process of a mobile collaborative robotic assistant modeled by the Markov decision process (MDP) framework is studied in this paper. The optimal state-action combinations of the MDP are calculated with the non-linear Bellman optimality equations. This system of equations can be solved with relative ease by the computational power of Wolfram Mathematica, where the obtained optimal action-values point to the optimal policy. Unlike other RL algorithms, …
Technion - Israel Institute of Technology（以色列理工学院）；Google Deepmind（谷歌DeepMind）
The monolithic approach to policy representation in Markov Decision Processes (MDPs) looks for a single policy that can be represented as a function from states to actions. For the monolithic approach to succeed (and this is not always possible), a complex feature representation is often necessary since the policy is a complex object that has to prescribe what actions to take all over the state space. This is especially true in large domains with complicated dynamics. It is also computationally inefficient to both learn and plan in MDPs using a complex monolithic approach. We present a differe…
Indian Institute of Science（印度科学学院）；IBM Research - India（IBM研究院（印度））
This paper considers two important problems -- on the supply-side and demand-side respectively and studies both in a unified framework. On the supply side, we study the problem of energy sharing among microgrids with the goal of maximizing profit obtained from selling power while at the same time not deviating much from the customer demand. On the other hand, under shortage of power, this problem becomes one of deciding the amount of power to be bought with dynamically varying prices. On the demand side, we consider the problem of optimally scheduling the time-adjustable demand - i.e., of load…
Real-Time Cascade Mitigation in Power Systems Using Influence Graph Improved by Reinforcement Learning
School of Mechanical and Electrical Engineering, Soochow University（苏州大学机械与电子工程学院）；Department of Computer Science, Iowa State University（计算机科学系，爱荷华州立大学）；Department of Mechanical Engineering, University of Akron（机械工程系，阿克伦大学）；Department of Computer and Information Technology, Purdue University（计算机与信息科技系，普渡大学）
Survey on Strategic Mining in Blockchain: A Reinforcement Learning Approach
Zhongguancun Laboratory（中关村实验室）；Peking University（北京大学）；Beihang University（北京航空航天大学）；Hangzhou International Innovation Institute of Beihang University（北京航空航天大学杭州国际创新研究院）
The polyhedral model allows a structured way of defining semantics-preserving transformations to improve the performance of a large class of loops. Finding profitable points in this space is a hard problem which is usually approached by heuristics that generalize from domain-expert knowledge. Existing problem formulations in state-of-the-art heuristics depend on the shape of particular loops, making it hard to leverage generic and more powerful optimization techniques from the machine learning domain. In this paper, we propose PolyGym, a shape-agnostic formulation for the space of legal transf…
Colorado State University（科罗拉多州立大学）；University of California, Los Angeles（加州大学洛杉矶分校）
Critical infrastructure systems such as electric power networks, water networks, and transportation systems play a major role in the welfare of any community. In the aftermath of disasters, their recovery is of paramount importance; orderly and efficient recovery involves the assignment of limited resources (a combination of human repair workers and machines) to repair damaged infrastructure components. The decision maker must also deal with uncertainty in the outcome of the resource-allocation actions during recovery. The manual assignment of resources seldom is optimal despite the expertise …
Chemical representations derived from deep learning are emerging as a powerful tool in areas such as drug discovery and materials innovation. Currently, this methodology has three major limitations - the cost of representation generation, risk of inherited bias, and the requirement for large amounts of data. We propose the use of multi-task learning in tandem with transfer learning to address these limitations directly. In order to avoid introducing unknown bias into multi-task learning through the task selection itself, we calculate task similarity through pairwise task affinity, and use this…
Development in the field of Single Board Computers (SBC) have been increasing for several years. They provide a good balance between computing performance and power consumption which is usually required for mobile platforms, like application in vehicles for Advanced Driver Assistance Systems (ADAS) and Autonomous Driving (AD). However, there is an ever-increasing need of more powerful and efficient SBCs which can run power intensive Deep Neural Networks (DNNs) in real-time and can also satisfy necessary functional safety requirements such as Automotive Safety Integrity Level (ASIL). ProAI is b…
Black-Box Privacy Attacks on Shared Representations in Multitask Learning
Khoury College of Computer Sciences, Northeastern University（克劳利计算机科学学院，东北大学）；Department of Computer Science, Boston University（计算机科学系，波士顿大学）；Google DeepMind, Advisor Only（谷歌DeepMind，顾问）
