Applying machine learning techniques to graph drawing has become an emergent area of research in visualization. In this paper, we interpret graph drawing as a multi-agent reinforcement learning (MARL) problem. We first demonstrate that a large number of classic graph drawing algorithms, including force-directed layouts and stress majorization, can be interpreted within the framework of MARL. Using this interpretation, a node in the graph is assigned to an agent with a reward function. Via multi-agent reward maximization, we obtain an aesthetically pleasing graph layout that is comparable to the outputs of classic algorithms. The main strength of a MARL framework for graph drawing is that it not only unifies a number of classic drawing algorithms in a general formulation but also supports the creation of novel graph drawing algorithms by introducing a diverse set of reward functions.
Design of Voltage-Controlled Oscillator (VCO) inductors is a laborious and time-consuming task that is conventionally done manually by human experts. In this paper, we propose a framework for automating the design of VCO inductors, using Reinforcement Learning (RL). We formulate the problem as a sequential procedure, where wire segments are drawn one after another, until a complete inductor is created. We then employ an RL agent to learn to draw inductors that meet certain target specifications. In light of the need to tweak the target specifications throughout the circuit design cycle, we als…
National University of Singapore（新加坡国立大学）；City University of Hong Kong（香港城市大学）；ByteDance AI lab（字节跳动人工智能实验室）
The Laplacian representation recently gains increasing attention for reinforcement learning as it provides succinct and informative representation for states, by taking the eigenvectors of the Laplacian matrix of the state-transition graph as state embeddings. Such representation captures the geometry of the underlying state space and is beneficial to RL tasks such as option discovery and reward shaping. To approximate the Laplacian representation in large (or even continuous) state spaces, recent works propose to minimize a spectral graph drawing objective, which however has infinitely many g…
Using Reinforcement Learning to Optimize the Global and Local Crossing Number
Technical University of Munich, Heilbronn, Germany（慕尼黑技术大学（海因斯贝格））；John Cabot University, Rome, Italy（约翰·卡博特大学）；Technical University of Munich, Garching, Germany（慕尼黑技术大学（戈林根））
Cash App Labs（Cash App实验室）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）
We convert the DeepMind Mathematics Dataset into a reinforcement learning environment by interpreting it as a program synthesis problem. Each action taken in the environment adds an operator or an input into a discrete compute graph. Graphs which compute correct answers yield positive reward, enabling the optimization of a policy to construct compute graphs conditioned on problem statements. Baseline models are trained using Double DQN on various subsets of problem types, demonstrating the capability to learn to correctly construct graphs despite the challenges of combinatorial explosion and n…
California Institute of Technology（加州理工学院）；Huntington Medical Research Institutes（亨廷顿医学研究所）；University of Chinese Academy of Sciences（中国科学院大学）
We model human decision-making behaviors in a risk-taking task using inverse reinforcement learning (IRL) for the purposes of understanding real human decision making under risk. To the best of our knowledge, this is the first work applying IRL to reveal the implicit reward function in human risk-taking decision making and to interpret risk-prone and risk-averse decision-making policies. We hypothesize that the state history (e.g. rewards and decisions in previous trials) are related to the human reward function, which leads to risk-averse and risk-prone decisions. We design features that refl…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Osaka University（大阪大学）；Advanced Telecommunication Research（先进电信研究所）
The recently successful Munchausen Reinforcement Learning (M-RL) features implicit Kullback-Leibler (KL) regularization by augmenting the reward function with logarithm of the current stochastic policy. Though significant improvement has been shown with the Boltzmann softmax policy, when the Tsallis sparsemax policy is considered, the augmentation leads to a flat learning curve for almost every problem considered. We show that it is due to the mismatch between the conventional logarithm and the non-logarithmic (generalized) nature of Tsallis entropy. Drawing inspiration from the Tsallis statis…
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as ε-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail.
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Osaka University（大阪大学）；Advanced Telecommunication Research（国际电气通信基础技术研究所）
Maximum Tsallis entropy (MTE) framework in reinforcement learning has gained popularity recently by virtue of its flexible modeling choices including the widely used Shannon entropy and sparse entropy. However, non-Shannon entropies suffer from approximation error and subsequent underperformance either due to its sensitivity or the lack of closed-form policy expression. To improve the tradeoff between flexibility and empirical performance, we propose to strengthen their error-robustness by enforcing implicit Kullback-Leibler (KL) regularization in MTE motivated by Munchausen DQN (MDQN). We do …
Gatsby Computational Neuroscience Unit, University College London（伦敦大学学院盖茨比计算神经科学单位）；Max Planck Institute for Biological Cybernetics（马克斯·普朗克生物控制论研究所）
We investigate how reinforcement learning agents can learn to cooperate. Drawing inspiration from human societies, in which successful coordination of many individuals is often facilitated by hierarchical organisation, we introduce Feudal Multi-agent Hierarchies (FMH). In this framework, a 'manager' agent, which is tasked with maximising the environmentally-determined reward function, learns to communicate subgoals to multiple, simultaneously-operating, 'worker' agents. Workers, which are rewarded for achieving managerial subgoals, take concurrent actions in the world. We outline the structure…
The asynchronous nature of the state-of-the-art reinforcement learning algorithms such as the Asynchronous Advantage Actor-Critic algorithm, makes them exceptionally suitable for CPU computations. However, given the fact that deep reinforcement learning often deals with interpreting visual information, a large part of the train and inference time is spent performing convolutions. In this work we present our results on learning strategies in Atari games using a Convolutional Neural Network, the Math Kernel Library and TensorFlow 0.11rc0 machine learning framework. We also analyze effects of asy…
We explore the reinforcement learning approach to designing controllers by extensively discussing the case of a quadcopter attitude controller. We provide all details allowing to reproduce our approach, starting with a model of the dynamics of a crazyflie 2.0 under various nominal and non-nominal conditions, including partial motor failures and wind gusts. We develop a robust form of a signal temporal logic to quantitatively evaluate the vehicle's behavior and measure the performance of controllers. The paper thoroughly describes the choices in training algorithms, neural net architecture, hyp…
Intelligent Autonomous Systems, Technische Universität Darmstadt（达姆施塔特工业大学智能自主系统（Intelligent Autonomous Systems, Technische Universität Darmstadt））；Department of Electrical Engineering and Automation, Aalto University（阿尔托大学电气工程与自动化系（Department of Electrical Engineering and Automation, Aalto University））
Curriculum reinforcement learning (CRL) improves the learning speed and stability of an agent by exposing it to a tailored series of tasks throughout learning. Despite empirical successes, an open question in CRL is how to automatically generate a curriculum for a given reinforcement learning (RL) agent, avoiding manual design. In this paper, we propose an answer by interpreting the curriculum generation as an inference problem, where distributions over tasks are progressively learned to approach the target task. This approach leads to an automatic curriculum generation, whose pace is controll…
Brown University（布朗大学）；Computer Science Department（计算机科学系）；Carney Institute for Brain Science（卡尼脑科学研究所）；Providence, RI 02912, USA（美国罗得岛州普罗维登斯市 02912）
A key question in reinforcement learning is how an intelligent agent can generalize knowledge across different inputs. By generalizing across different inputs, information learned for one input can be immediately reused for improving predictions for another input. Reusing information allows an agent to compute an optimal decision-making strategy using less data. State representation is a key element of the generalization process, compressing a high-dimensional input space into a low-dimensional latent state space. This article analyzes properties of different latent state spaces, leading to ne…
This work considers two distinct settings: imitation learning and goal-conditioned reinforcement learning. In either case, effective solutions require the agent to reliably reach a specified state (a goal), or set of states (a demonstration). Drawing a connection between probabilistic long-term dynamics and the desired value function, this work introduces an approach which utilizes recent advances in density estimation to effectively learn to reach a given state. As our first contribution, we use this approach for goal-conditioned reinforcement learning and show that it is both efficient and d…
SPOTting the Future: Lookahead Explanations for Deep Reinforcement Learning
Benin School of Computer Science and Engineering, The Hebrew University of Jerusalem（耶路撒冷希伯来大学贝林计算机科学与工程学院）；Hebrew University Business School, Data Science Department, The Hebrew University of Jerusalem（耶路撒冷希伯来大学希伯来大学商学院数据科学系）
Preference Elicitation for Offline Reinforcement Learning
ETH AI Center（ETH人工智能中心）；ETH Zürich（苏黎世联邦理工学院）；MPI for Intelligent Systems（智能系统马克斯·普朗克研究所）；ELLIS Institute Tübingen（图宾根ELLIS研究所）；University of Zürich（苏黎世大学）
Rochester Institute of Technology（罗切斯特理工学院）；Pennsylvania State University（宾夕法尼亚州立大学）
In humans, perceptual awareness facilitates the fast recognition and extraction of information from sensory input. This awareness largely depends on how the human agent interacts with the environment. In this work, we propose active neural generative coding, a computational framework for learning action-driven generative models without backpropagation of errors (backprop) in dynamic environments. Specifically, we develop an intelligent agent that operates even with sparse rewards, drawing inspiration from the cognitive theory of planning as inference. We demonstrate on several simple control p…
We present a new algorithm to generate minimal, stable, and symbolic corrections to an input that will cause a neural network with ReLU activations to change its output. We argue that such a correction is a useful way to provide feedback to a user when the network's output is different from a desired output. Our algorithm generates such a correction by solving a series of linear constraint satisfaction problems. The technique is evaluated on three neural network models: one predicting whether an applicant will pay a mortgage, one predicting whether a first-order theorem can be proved efficient…
We propose an approach for inverse reinforcement learning from hetero-domain which learns a reward function in the simulator, drawing on the demonstrations from the real world. The intuition behind the method is that the reward function should not only be oriented to imitate the experts, but should encourage actions adjusted for the dynamics difference between the simulator and the real world. To achieve this, the widely used GAN-inspired IRL method is adopted, and its discriminator, recognizing policy-generating trajectories, is modified with the quantification of dynamics difference. The tra…
Microsoft Research（微软研究院）；Google Inc.（谷歌公司）；Citadel（城堡投资）；Carnegie Mellon University（卡内基梅隆大学）；Amazon AI（亚马逊人工智能）
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as $ε$-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail.
Hanjin Heavy Industries and Construction Co., LTD（韩进重工业建设有限公司）；Yonsei University（延世大学）
The purpose of accounting audit is to have clear understanding on the financial activities of a company, which can be enhanced by machine learning or reinforcement learning as numeric analysis better than manual analysis can be made. For the purpose of assessment on the relevance, completeness and accuracy of the information produced by entity pertaining to the newly implemented International Financial Reporting Standard 16 Lease (IFRS 16) is one of such candidates as its characteristic of requiring the understanding on the nature of contracts and its complete analysis from listing up without …
Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic Perspective
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Xi’an Jiaotong University（西安交通大学）；SenseTime Research（商汤科技研究院）；Peking University（北京大学）；The Chinese University of Hong Kong（香港中文大学）
Reinforcement learning refers to a group of methods from artificial intelligence where an agent performs learning through trial and error. It differs from supervised learning, since reinforcement learning requires no explicit labels; instead, the agent interacts continuously with its environment. That is, the agent starts in a specific state and then performs an action, based on which it transitions to a new state and, depending on the outcome, receives a reward. Different strategies (e.g. Q-learning) have been proposed to maximize the overall reward, resulting in a so-called policy, which def…
Communication in multi-agent reinforcement learning has been drawing attention recently for its significant role in cooperation. However, multi-agent systems may suffer from limitations on communication resources and thus need efficient communication techniques in real-world scenarios. According to the Shannon-Hartley theorem, messages to be transmitted reliably in worse channels require lower entropy. Therefore, we aim to reduce message entropy in multi-agent communication. A fundamental challenge is that the gradients of entropy are either 0 or infinity, disabling gradient-based methods. To …
We propose a planning and perception mechanism for a robot (agent), that can only observe the underlying environment partially, in order to solve an image classification problem. A three-layer architecture is suggested that consists of a meta-layer that decides the intermediate goals, an action-layer that selects local actions as the agent navigates towards a goal, and a classification-layer that evaluates the reward and makes a prediction. We design and implement these layers using deep reinforcement learning. A generalized policy gradient algorithm is utilized to learn the parameters of thes…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
Model-free deep reinforcement learning (RL) algorithms have been widely used for a range of complex control tasks. However, slow convergence and sample inefficiency remain challenging problems in RL, especially when handling continuous and high-dimensional state spaces. To tackle this problem, we propose a general acceleration method for model-free, off-policy deep RL algorithms by drawing the idea underlying regularized Anderson acceleration (RAA), which is an effective approach to accelerating the solving of fixed point problems with perturbations. Specifically, we first explain how policy i…
Despite the recent successes of reinforcement learning in games and robotics, it is yet to become broadly practical. Sample efficiency and unreliable performance in rare but challenging scenarios are two of the major obstacles. Drawing inspiration from the effectiveness of deliberate practice for achieving expert-level human performance, we propose a new adversarial sampling approach guided by a failure predictor named "CoachNet". CoachNet is trained online along with the agent to predict the probability of failure. This probability is then used in a stochastic sampling process to guide the ag…
In-Context Reinforcement Learning via Communicative World Models
Department of Computer and Information Sciences, Fordham University（福特汉姆大学计算机与信息科学系）；Department of Systems Engineering, City University of Hong Kong（香港城市大学系统工程系）；IBM Research（IBM研究院）
Ocean University of China（中国海洋大学）；Bilkent University（比尔肯特大学）；University of Oxford（牛津大学）；Delft University of Technology（代尔夫特理工大学）
Interactive reinforcement learning provides a way for agents to learn to solve tasks from evaluative feedback provided by a human user. Previous research showed that humans give copious feedback early in training but very sparsely thereafter. In this article, we investigate the potential of agent learning from trainers' facial expressions via interpreting them as evaluative feedback. To do so, we implemented TAMER which is a popular interactive reinforcement learning method in a reinforcement-learning benchmark problem --- Infinite Mario, and conducted the first large-scale study of TAMER invo…
Columbia University（哥伦比亚大学）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）
Drawing an inspiration from behavioral studies of human decision making, we propose here a general parametric framework for a reinforcement learning problem, which extends the standard Q-learning approach to incorporate a two-stream framework of reward processing with biases biologically associated with several neurological and psychiatric conditions, including Parkinson's and Alzheimer's diseases, attention-deficit/hyperactivity disorder (ADHD), addiction, and chronic pain. For AI community, the development of agents that react differently to different types of rewards can enable us to unders…
Using touch devices to navigate in virtual 3D environments such as computer assisted design (CAD) models or geographical information systems (GIS) is inherently difficult for humans, as the 3D operations have to be performed by the user on a 2D touch surface. This ill-posed problem is classically solved with a fixed and handcrafted interaction protocol, which must be learned by the user. We propose to automatically learn a new interaction protocol allowing to map a 2D user input to 3D actions in virtual environments using reinforcement learning (RL). A fundamental problem of RL methods is the …
Modern robotics applications that involve human-robot interaction require robots to be able to communicate with humans seamlessly and effectively. Natural language provides a flexible and efficient medium through which robots can exchange information with their human partners. Significant advancements have been made in developing robots capable of interpreting free-form instructions, but less attention has been devoted to endowing robots with the ability to generate natural language. We propose a navigational guide model that enables robots to generate natural language instructions that allow …
The prevalent approach in self-supervised image generation is to operate on pixel level representations. While this approach can produce high quality images, it cannot benefit from the simplicity and innate quality of vectorization. Here we present a drawing agent that operates on stroke-level representation of images. At each time step, the agent first assesses the current canvas and decides whether to stop or keep drawing. When a 'draw' decision is made, the agent outputs a program indicating the stroke to be drawn. As a result, it produces a final raster image by drawing the strokes on a ca…
