Reinforcement learning agents have demonstrated remarkable achievements in simulated environments. Data efficiency poses an impediment to carrying this success over to real environments. The design of data-efficient agents calls for a deeper understanding of information acquisition and representation. We discuss concepts and regret analysis that together offer principled guidance. This line of thinking sheds light on questions of what information to seek, how to seek that information, and what information to retain. To illustrate concepts, we design simple agents that build on them and present computational results that highlight data efficiency.
Xi’an Jiaotong University（西安交通大学）；The Hong Kong Polytechnic University（香港理工大学）
Mixed-precision quantization mostly predetermines the model bit-width settings before actual training due to the non-differential bit-width sampling process, obtaining sub-optimal performance. Worse still, the conventional static quality-consistent training setting, i.e., all data is assumed to be of the same quality across training and inference, overlooks data quality changes in real-world applications which may lead to poor robustness of the quantized models. In this paper, we propose a novel Data Quality-aware Mixed-precision Quantization framework, dubbed DQMQ, to dynamically adapt quanti…
BitRL: Reinforcement Learning with 1-bit Quantized Language Models for Resource-Constrained Edge Deployment
Department of Computer Science BRAC University Dhaka 1212, Bangladesh；Department of Computer Science Missouri State University Springfield, MO, USA；Department of Computer Science \& Engineering Prime University Dhaka, Bangladesh；Department of Computer Science \& Engineering German University Bangladesh Dhaka, Bangladesh；Department of Information Technology Jahangirnagar University Dhaka, Bangladesh
Reinforcement Learning faces an important challenge in partial observable environments that has long-term dependencies. In order to learn in an ambiguous environment, an agent has to keep previous perceptions in a memory. Earlier memory based approaches use a fixed method to determine what to keep in the memory, which limits them to certain problems. In this study, we follow the idea of giving the control of the memory to the agent by allowing it to have memory-changing actions. This learning mechanism is supported by an intrinsic motivation to memorize rare observations that can help the agen…
New York University（纽约大学）；Chalmers University of Technology（查尔姆斯理工大学）；University of Parma（帕尔马大学）；Duke University（杜克大学）
In this paper, we use reinforcement learning to find effective decoding strategies for binary linear codes. We start by reviewing several iterative decoding algorithms that involve a decision-making process at each step, including bit-flipping (BF) decoding, residual belief propagation, and anchor decoding. We then illustrate how such algorithms can be mapped to Markov decision processes allowing for data-driven learning of optimal decision strategies, rather than basing decisions on heuristics or intuition. As a case study, we consider BF decoding for both the binary symmetric and additive wh…
National Yang Ming Chiao Tung University（国立阳明交通大学）
This paper presents a reinforcement learning (RL) framework that leverages Frank-Wolfe policy optimization to address frame-level bit allocation for HEVC/H.265. Most previous RL-based approaches adopt the single-critic design, which weights the rewards for distortion minimization and rate regularization by an empirically chosen hyper-parameter. More recently, the dual-critic design is proposed to update the actor network by alternating the rate and distortion critics. However, the convergence of training is not guaranteed. To address this issue, we introduce Neural Frank-Wolfe Policy Optimizat…
BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning
Zhejiang University（浙江大学）；Zhejiang Lab（浙江省实验室）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Nanyang Technological University（南洋理工大学）；Rutgers University（罗格斯大学）
Department of Electrical Engineering, Princeton University（普林斯顿大学电气工程系）；Department of Electrical Engineering, POSTECH（浦项科技大学电气工程系）
The use of one-bit analog-to-digital converters (ADCs) at a receiver is a power-efficient solution for future wireless systems operating with a large signal bandwidth and/or a massive number of receive radio frequency chains. This solution, however, induces a high channel estimation error and therefore makes it difficult to perform the optimal data detection that requires perfect knowledge of likelihood functions at the receiver. In this paper, we propose a likelihood function learning method for multiple-input multiple-output (MIMO) systems with one-bit ADCs using a reinforcement learning app…
What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Nanjing University（南京大学）
University of Siena（锡耶纳大学）；University of Chieti-Pescara（基耶蒂-佩斯卡拉大学）
A Pseudo-Random Number Generator (PRNG) is any algorithm generating a sequence of numbers approximating properties of random numbers. These numbers are widely employed in mid-level cryptography and in software applications. Test suites are used to evaluate PRNGs quality by checking statistical properties of the generated sequences. These sequences are commonly represented bit by bit. This paper proposes a Reinforcement Learning (RL) approach to the task of generating PRNGs from scratch by learning a policy to solve a partially observable Markov Decision Process (MDP), where the full state is t…
Recurrent meta reinforcement learning (meta-RL) agents are agents that employ a recurrent neural network (RNN) for the purpose of "learning a learning algorithm". After being trained on a pre-specified task distribution, the learned weights of the agent's RNN are said to implement an efficient learning algorithm through their activity dynamics, which allows the agent to quickly solve new tasks sampled from the same distribution. However, due to the black-box nature of these agents, the way in which they work is not yet fully understood. In this study, we shed light on the internal working mech…
Northeast Electric Power University（东北电力大学）；Hanyang University（汉阳大学）
The emerging cryptocurrency market has lately received great attention for asset allocation due to its decentralization uniqueness. However, its volatility and brand new trading mode have made it challenging to devising an acceptable automatically-generating strategy. This study proposes a framework for automatic high-frequency bitcoin transactions based on a deep reinforcement learning algorithm-proximal policy optimization (PPO). The framework creatively regards the transaction process as actions, returns as awards and prices as states to align with the idea of reinforcement learning. It com…
One of the most significant bottleneck in training large scale machine learning models on parameter server (PS) is the communication overhead, because it needs to frequently exchange the model gradients between the workers and servers during the training iterations. Gradient quantization has been proposed as an effective approach to reducing the communication volume. One key issue in gradient quantization is setting the number of bits for quantizing the gradients. Small number of bits can significantly reduce the communication overhead while hurts the gradient accuracies, and vise versa. An id…
Recent developments have established the vulnerability of deep Reinforcement Learning (RL) to policy manipulation attacks via adversarial perturbations. In this paper, we investigate the robustness and resilience of deep RL to training-time and test-time attacks. Through experimental results, we demonstrate that under noncontiguous training-time attacks, Deep Q-Network (DQN) agents can recover and adapt to the adversarial conditions by reactively adjusting the policy. Our results also show that policies learned under adversarial perturbations are more robust to test-time attacks. Furthermore, …
University of California San Diego（加州大学圣地亚哥分校）；Google Brain（谷歌大脑）
Deep Neural Networks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN computation and storage by decreasing the bitwidth of network encodings. Recent research affirms that carefully selecting the quantization levels for each layer can preserve the accuracy while pushing the bitwidth below eight bits. However, without arduous manual effort, this deep quantization can lead to significant accuracy loss, leaving it in a position of questionable utility. As such, deep quantization opens a l…
What is the objective of reasoning with reinforcement learning?
Department of Statistics and Data Science, The Wharton School, University of Pennsylvania（统计与数据科学系，沃森商学院，宾夕法尼亚大学）；Department of Electrical Engineering and Computer Sciences, University of California, Berkeley（电气工程与计算机科学系，加州大学伯克利分校）
Carnegie Mellon University（卡内基梅隆大学）；City University of Hong Kong（香港城市大学）；University of Cambridge（剑桥大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Amsterdam（阿姆斯特丹大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
One practical challenge in reinforcement learning (RL) is how to make quick adaptations when faced with new environments. In this paper, we propose a principled framework for adaptive RL, called \textit{AdaRL}, that adapts reliably and efficiently to changes across domains with a few samples from the target domain, even in partially observable environments. Specifically, we leverage a parsimonious graphical representation that characterizes structural relationships over variables in the RL system. Such graphical representations provide a compact way to encode what and where the changes across …
Mila - McGill University（米拉 - 麦吉尔大学）；DeepMind；Brown University（布朗大学）
Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the features of their environment and the actions that are feasible. Gibson (1977) coined the term "affordances" to describe the fact that certain states enable an agent to do certain actions, in the context of embodied agents. In this paper, we develop a theory of affordances for agents who learn and plan in Markov Decision Processes. Affordances play a dual role in this case. On one hand, they allow faster planning, by reduci…
Automatic design is a promising approach to generating control software for robot swarms. So far, automatic design has relied on mission-specific objective functions to specify the desired collective behavior. In this paper, we explore the possibility to specify the desired collective behavior via demonstrations. We develop Demo-Cho, an automatic design method that combines inverse reinforcement learning with automatic modular design of control software for robot swarms. We show that, only on the basis of demonstrations and without the need to be provided with an explicit objective function, D…
We demonstrate a novel application of online transfer learning for a digital assets trading agent. This agent uses a powerful feature space representation in the form of an echo state network, the output of which is made available to a direct, recurrent reinforcement learning agent. The agent learns to trade the XBTUSD (Bitcoin versus US Dollars) perpetual swap derivatives contract on BitMEX on an intraday basis. By learning from the multiple sources of impact on the quadratic risk-adjusted utility that it seeks to maximise, the agent avoids excessive over-trading, captures a funding profit, a…
University of Alberta（阿尔伯塔大学）；Noah’s Ark Lab, Huawei Technologies Canada（华为加拿大诺亚方舟实验室）
Auxiliary tasks have been argued to be useful for representation learning in reinforcement learning. Although many auxiliary tasks have been empirically shown to be effective for accelerating learning on the main task, it is not yet clear what makes useful auxiliary tasks. Some of the most promising results are on the pixel control, reward prediction, and the next state prediction auxiliary tasks; however, the empirical results are mixed, showing substantial improvements in some cases and marginal improvements in others. Careful investigations of how auxiliary tasks help the learning of the ma…
TECNALIA, Basque Research and Technology Alliance (BRTA)（TECNALIA，巴斯克研究与技术联盟）；University of the Basque Country (UPV/EHU)（巴斯克大学）
In the early stages of human life, babies develop their skills by exploring different scenarios motivated by their inherent satisfaction rather than by extrinsic rewards from the environment. This behavior, referred to as intrinsic motivation, has emerged as one solution to address the exploration challenge derived from reinforcement learning environments with sparse rewards. Diverse exploration approaches have been proposed to accelerate the learning process over single- and multi-agent problems with homogeneous agents. However, scarce studies have elaborated on collaborative learning framewo…
Mila（米拉研究所）；McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）
To achieve general artificial intelligence, reinforcement learning (RL) agents should learn not only to optimize returns for one specific task but also to constantly build more complex skills and scaffold their knowledge about the world, without forgetting what has already been learned. In this paper, we discuss the desired characteristics of environments that can support the training and evaluation of lifelong reinforcement learning agents, review existing environments from this perspective, and propose recommendations for devising suitable environments in the future.
High performance packet classification is a key component to support scalable network applications like firewalls, intrusion detection, and differentiated services. With ever increasing in the line-rate in core networks, it becomes a great challenge to design a scalable and high performance packet classification solution using hand-tuned heuristics approaches. In this paper, we present a scalable learning-based packet classification engine and its performance evaluation. By exploiting the sparsity of ruleset, our algorithm uses a few effective bits (EBs) to extract a large number of candidate …
Google research（谷歌研究）；Deepmind（深度思维）；The Technion - Israel Institute of Technology（以色列理工学院）
Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant. In such cases, it is sometimes easier to learn which actions not to take. In this work, we propose the Action-Elimination Deep Q-Network (AE-DQN) architecture that combines a Deep RL algorithm with an Action Elimination Network (AEN) that eliminates sub-optimal actions. The AEN is trained to predict invalid actions, supervised by an external elimination signal provided by the environment. Simulatio…
Tel Aviv University（特拉维夫大学）；École Normale Supérieure（巴黎高等师范学院）；PSL Research University（巴黎文理研究大学）；Sorbonne University（索邦大学）；Université Paris Diderot（巴黎第七大学）
Traditional memory writing operations proceed one bit at a time, where e.g. an individual magnetic domain is force-flipped by a localized external field. One way to increase material storage capacity would be to write several bits at a time in the bulk of the material. However, the manipulation of bits is commonly done through quasi-static operations. While simple to model, this method is known to reduce memory capacity. In this paper, we demonstrate how a reinforcement learning agent can exploit the dynamical response of a simple multi-bit mechanical system to restore its memory to full capac…
We contribute to micro-data model-based reinforcement learning (MBRL) by rigorously comparing popular generative models using a fixed (random shooting) control agent. We find that on an environment that requires multimodal posterior predictives, mixture density nets outperform all other models by a large margin. When multimodality is not required, our surprising finding is that we do not need probabilistic posterior predictives: deterministic models are on par, in fact they consistently (although non-significantly) outperform their probabilistic counterparts. We also found that heteroscedastic…
University of Hamburg（汉堡大学）；Universidad Central de Chile（智利中央大学）；Osaka University（大阪大学）；National Institute of Information and Communications Technology（信息通信研究机构）
Interactive reinforcement learning has become an important apprenticeship approach to speed up convergence in classic reinforcement learning problems. In this regard, a variant of interactive reinforcement learning is policy shaping which uses a parent-like trainer to propose the next action to be performed and by doing so reduces the search space by advice. On some occasions, the trainer may be another artificial agent which in turn was trained using reinforcement learning methods to afterward becoming an advisor for other learner-agents. In this work, we analyze internal representations and …
Deep Q Network (DQN) firstly kicked the door of deep reinforcement learning (DRL) via combining deep learning (DL) with reinforcement learning (RL), which has noticed that the distribution of the acquired data would change during the training process. DQN found this property might cause instability for training, so it proposed effective methods to handle the downside of the property. Instead of focusing on the unfavourable aspects, we find it critical for RL to ease the gap between the estimated data distribution and the ground truth data distribution while supervised learning (SL) fails to do…
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息与电子工程学院）；VTT Technical Research Centre of Finland（芬兰VTT技术研究中心）；Zhejiang Lab（之江实验室）
We introduce a new semantic communication mechanism - SemanticRL, whose key idea is to preserve the semantic information instead of strictly securing the bit-level precision. Unlike previous methods that mainly concentrate on the network or structure design, we revisit the learning process and point out the semantic blindness of commonly used objective functions. To address this semantic gap, we introduce a schematic shift that learns from semantic similarity, instead of relying on conventional paired bit-level supervisions like cross entropy and bit error rate. However, developing such a sema…
University of Surrey（萨里大学）；Amazon Web Services（亚马逊云科技）；Alan Turing Institute（艾伦·图灵研究所）
We present a novel form of explanation for Reinforcement Learning, based around the notion of intended outcome. These explanations describe the outcome an agent is trying to achieve by its actions. We provide a simple proof that general methods for post-hoc explanations of this nature are impossible in traditional reinforcement learning. Rather, the information needed for the explanations must be collected in conjunction with training the agent. We derive approaches designed to extract local explanations based on intention for several variants of Q-function approximation and prove consistency …
In recent years, on-policy reinforcement learning (RL) has been successfully applied to many different continuous control tasks. While RL algorithms are often conceptually simple, their state-of-the-art implementations take numerous low- and high-level design decisions that strongly affect the performance of the resulting agents. Those choices are usually not extensively discussed in the literature, leading to discrepancy between published descriptions of algorithms and their implementations. This makes it hard to attribute progress in RL and slows down overall progress [Engstrom'20]. As a ste…
University of Edinburgh（爱丁堡大学）；University College London（伦敦大学学院）；Peking University（北京大学）；BIGAI（北京通用人工智能研究院）
We study a novel setting in offline reinforcement learning (RL) where a number of distributed machines jointly cooperate to solve the problem but only one single round of communication is allowed and there is a budget constraint on the total number of information (in terms of bits) that each machine can send out. For value function prediction in contextual bandits, and both episodic and non-episodic MDPs, we establish information-theoretic lower bounds on the minimax risk for distributed statistical estimators; this reveals the minimum amount of communication required by any offline RL algorit…
A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model
Center for Quantum Computer Science, Faculty of Computing（量子计算机科学中心，计算学院）；University of Latvia（拉脱维亚大学）；HUN-REN Alfréd Rényi Institute of Mathematics（匈牙利-中国阿尔弗雷德·雷尼数学研究所）
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；Facebook
Client-side video players employ adaptive bitrate (ABR) algorithms to optimize user quality of experience (QoE). We evaluate recently proposed RL-based ABR methods in Facebook's web-based video streaming platform. Real-world ABR contains several challenges that requires customized designs beyond off-the-shelf RL algorithms -- we implement a scalable neural network architecture that supports videos with arbitrary bitrate encodings; we design a training method to cope with the variance resulting from the stochasticity in network conditions; and we leverage constrained Bayesian optimization for r…
K. J. Somaiya College of Engineering（K·J·索马伊亚工程学院）
For a long time predicting, studying and analyzing financial indices has been of major interest for the financial community. Recently, there has been a growing interest in the Deep-Learning community to make use of reinforcement learning which has surpassed many of the previous benchmarks in a lot of fields. Our method provides a feature rich environment for the reinforcement learning agent to work on. The aim is to provide long term profits to the user so, we took into consideration the most reliable technical indicators. We have also developed a custom indicator which would provide better in…
随着云计算的使用不断增加，控制成本变得越来越重要。然而，有证据表明，30%-45%的云支出被浪费了。现有的云供应工具通常依赖于训练有素的人类专家来指定要监控的内容、触发动作的阈值和动作。在本文中，我们将探索使用强化学习（RL）来获取平衡性能和支出的策略，允许人们指定他们想要什么，而不是如何去做，从而最大限度地减少对云专业知识的需求。使用CloudSim模拟器进行表格式、深度和决斗式双深度Q学习的实证结果显示了RL的实用性和这些方法的相对优点。我们还演示了有效的策略迁移学习，从一个非常简单的模拟器到CloudSim，下一步是从CloudSim迁移到Amazon Web Services物理环境。
Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards
Tsinghua University（清华大学）；Renmin University of China（中国人民大学）；Institute of Information Engineering, CAS（中国科学院信息工程研究所）；USTC（中国科学技术大学）；The Australian National University（澳大利亚国立大学）；Peking University（北京大学）；University of Macau（澳门大学）
This paper formulates the polar-code construction problem for the successive-cancellation list (SCL) decoder as a maze-traversing game, which can be solved by reinforcement learning techniques. The proposed method provides a novel technique for polar-code construction that no longer depends on sorting and selecting bit-channels by reliability. Instead, this technique decides whether the input bits should be frozen in a purely sequential manner. The equivalence of optimizing the polar-code construction for the SCL decoder under this technique and maximizing the expected reward of traversing a m…
