Recent approaches for modelling dynamics of physical systems with neural networks enforce Lagrangian or Hamiltonian structure to improve prediction and generalization. However, when coordinates are embedded in high-dimensional data such as images, these approaches either lose interpretability or can only be applied to one particular example. We introduce a new unsupervised neural network model that learns Lagrangian dynamics from images, with interpretability that benefits prediction and control. The model infers Lagrangian dynamics on generalized coordinates that are simultaneously learned with a coordinate-aware variational autoencoder (VAE). The VAE is designed to account for the geometry of physical systems composed of multiple rigid bodies in the plane. By inferring interpretable Lagrangian dynamics, the model learns physical system properties, such as kinetic and potential energy, which enables long-term prediction of dynamics in the image space and synthesis of energy-based controllers.
National Institute of Informatics（国立信息学研究所）；KTH Royal Institute of Technology（KTH皇家理工学院）；University of Edinburgh（爱丁堡大学）
Generating versatile and appropriate synthetic speech requires control over the output expression separate from the spoken text. Important non-textual speech variation is seldom annotated, in which case output control must be learned in an unsupervised fashion. In this paper, we perform an in-depth study of methods for unsupervised learning of control in statistical speech synthesis. For example, we show that popular unsupervised training heuristics can be interpreted as variational inference in certain autoencoder models. We additionally connect these models to VQ-VAEs, another, recently-prop…
Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve perceptually-specified goals using only a stream of observations and actions. Our agent simultaneously learns a goal-conditioned policy and a goal achievement reward function that measures how similar a state is to the goal state. This dual optimization leads to a co-operative game, giving rise to a learned reward function that reflects similarity in controllable asp…
Norwegian University of Life Sciences（挪威生命科学大学）；Rosim Company（Rosim公司）
Exploiting capacity of sewer system using decentralized control is a cost effective mean of minimizing the overflow. Given the size of the real sewer system, exploiting all the installed control structures in the sewer pipes can be challenging. This paper presents a divide and conquer solution to implement decentralized control measures based on unsupervised learning algorithms. A sewer system is first divided into a number of subcatchments. A series of natural and built factors that have the impact on sewer system performance is then collected. Clustering algorithms are then applied to groupi…
Recent generative adversarial networks (GANs) are able to generate impressive photo-realistic images. However, controllable generation with GANs remains a challenging research problem. Achieving controllable generation requires semantically interpretable and disentangled factors of variation. It is challenging to achieve this goal using simple fixed distributions such as Gaussian distribution. Instead, we propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training. Self-training provides an iterative feedback in the GAN training, f…
Technische Universität München（慕尼黑工业大学）；sensed.io UG (haftungsbeschränkt)（sensed.io有限责任公司）；fortiss（福蒂斯研究所）
Tactile information is important for gripping, stable grasp, and in-hand manipulation, yet the complexity of tactile data prevents widespread use of such sensors. We make use of an unsupervised learning algorithm that transforms the complex tactile data into a compact, latent representation without the need to record ground truth reference data. These compact representations can either be used directly in a reinforcement learning based controller or can be used to calibrate the tactile sensor to physical quantities with only a few datapoints. We show the quality of our latent representation by…
Non-convex AC optimal power flow (AC-OPF) is a fundamental optimization problem in power system analysis. The computational complexity of conventional solvers is typically high and not suitable for large-scale networks in real-time operation. Hence, deep learning based approaches have gained intensive attention to conduct the time-consuming training process offline. Supervised learning methods may yield a feasible AC-OPF solution with a small optimality gap. However, they often need conventional solvers to generate the training dataset. This paper proposes an end-to-end unsupervised learning b…
Faculty of Computer Engineering Amirkabi University of Technology Tehran, Iran
Video Generation is a relatively new and yet popular subject in machine learning due to its vast variety of potential applications and its numerous challenges. Current methods in Video Generation provide the user with little or no control over the exact specification of how the objects in the generate video are to be moved and located at each frame, that is, the user can't explicitly control how each object in the video should move. In this paper we propose a novel method that allows the user to move any number of objects of a single initial frame just by drawing bounding boxes over those obje…
Tel Aviv University（特拉维夫大学）；Hebrew University, Jerusalem（耶路撒冷希伯来大学）
The emergence of deep generative models has recently enabled the automatic generation of massive amounts of graphical content, both in 2D and in 3D. Generative Adversarial Networks (GANs) and style control mechanisms, such as Adaptive Instance Normalization (AdaIN), have proved particularly effective in this context, culminating in the state-of-the-art StyleGAN architecture. While such models are able to learn diverse distributions, provided a sufficiently large training set, they are not well-suited for scenarios where the distribution of the training data exhibits a multi-modal behavior. In …
Osaka University（大阪大学）；Graduate School of Engineering Science（工程科学研究生院）
Deep reinforcement learning (DRL) has attracted much attention as an approach to solve optimal control problems without mathematical models of systems. On the other hand, in general, constraints may be imposed on optimal control problems. In this study, we consider the optimal control problems with constraints to complete temporal control tasks. We describe the constraints using signal temporal logic (STL), which is useful for time sensitive control tasks since it can specify continuous signals within bounded time intervals. To deal with the STL constraints, we introduce an extended constraine…
Learning Physically Consistent Lagrangian Control Models Without Acceleration Measurements
Sorbonne University（索邦大学）；Institut des Systèmes Intelligents et de Robotique（智能系统与机器人研究所）；Criteo AI Lab Paris（Criteo巴黎AI实验室）；Centre of Robotics（机器人中心）；MINES Paris-PSL PSL University（巴黎矿学院PSL大学）
As a network-based functional approximator, we have proposed a "Lagrangian Density Space-Time Deep Neural Networks" (LDDNN) topology. It is qualified for unsupervised training and learning to predict the dynamics of underlying physical science governed phenomena. The prototypical network respects the fundamental conservation laws of nature through the succinctly described Lagrangian and Hamiltonian density of the system by a given data-set of generalized nonlinear partial differential equations. The objective is to parameterize the Lagrangian density over a neural network and directly learn fr…
Technische Universität Darmstadt（达姆施塔特工业大学）；ABB Corporate Research Center Germany（ABB德国企业研究中心）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Applying Deep Learning to control has a lot of potential for enabling the intelligent design of robot control laws. Unfortunately common deep learning approaches to control, such as deep reinforcement learning, require an unrealistic amount of interaction with the real system, do not yield any performance guarantees, and do not make good use of extensive insights from model-based control. In particular, common black-box approaches -- that abandon all insight from control -- are not suitable for complex robot systems. We propose a deep control approach as a bridge between the solid theoretical …
Predictive Lagrangian Optimization for Constrained Reinforcement Learning
Weiyang College, Tsinghua University（清华大学未央学院）；Xingjian College, Tsinghua University（清华大学行健学院）；School of Vehicle and Mobility, Tsinghua University（清华大学车辆与出行学院）；College of Artificial Intelligence, Tsinghua University（清华大学人工智能学院）；Department of Mathematical Sciences, Tsinghua University（清华大学数学科学系）；School of Mechanical Engineering, University of Science and Technology Beijing（北京科技大学机械工程学院）
We introduce Contrastive Intrinsic Control (CIC), an algorithm for unsupervised skill discovery that maximizes the mutual information between state-transitions and latent skill vectors. CIC utilizes contrastive learning between state-transitions and skills to learn behavior embeddings and maximizes the entropy of these embeddings as an intrinsic reward to encourage behavioral diversity. We evaluate our algorithm on the Unsupervised Reinforcement Learning Benchmark, which consists of a long reward-free pre-training phase followed by a short adaptation phase to downstream tasks with extrinsic re…
Safety is essential for reinforcement learning (RL) applied in the real world. Adding chance constraints (or probabilistic constraints) is a suitable way to enhance RL safety under uncertainty. Existing chance-constrained RL methods like the penalty methods and the Lagrangian methods either exhibit periodic oscillations or learn an over-conservative or unsafe policy. In this paper, we address these shortcomings by proposing a separated proportional-integral Lagrangian (SPIL) algorithm. We first review the constrained policy optimization process from a feedback control perspective, which regard…
The brain can learn to execute a wide variety of tasks quickly and efficiently. Nevertheless, most of the mechanisms that enable us to learn are unclear or incredibly complicated. Recently, considerable efforts have been made in neuroscience and artificial intelligence to understand and model the structure and mechanisms behind the amazing learning capability of the brain. However, in the current understanding of cognitive neuroscience, it is widely accepted that synaptic plasticity plays an essential role in our amazing learning capability. This mechanism is also known as the Credit Assignmen…
Safety is essential for reinforcement learning (RL) applied in real-world tasks like autonomous driving. Chance constraints which guarantee the satisfaction of state constraints at a high probability are suitable to represent the requirements in real-world environment with uncertainty. Existing chance constrained RL methods like the penalty method and the Lagrangian method either exhibit periodic oscillations or cannot satisfy the constraints. In this paper, we address these shortcomings by proposing a separated proportional-integral Lagrangian (SPIL) algorithm. Taking a control perspective, w…
University of California, Berkeley, BAIR（加州大学伯克利分校伯克利人工智能研究所）
We present CURL: Contrastive Unsupervised Representations for Reinforcement Learning. CURL extracts high-level features from raw pixels using contrastive learning and performs off-policy control on top of the extracted features. CURL outperforms prior pixel-based methods, both model-based and model-free, on complex tasks in the DeepMind Control Suite and Atari Games showing 1.9x and 1.2x performance gains at the 100K environment and interaction steps benchmarks respectively. On the DeepMind Control Suite, CURL is the first image-based algorithm to nearly match the sample-efficiency of methods …
While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where aspects of the environment needed to compute progress are not directly accessible. To enable robots to autonomously learn skills, we instead consider the problem of reinforcement learning without access to rewards. We aim to learn an unsupervised embedding space under which the robot can measure progress towards a goal for itself. Our approach explicitly opt…
Programmable logic controller (PLC) based industrial control systems (ICS) are used to monitor and control critical infrastructure. Integration of communication networks and an Internet of Things approach in ICS has increased ICS vulnerability to cyber-attacks. This work proposes novel unsupervised machine learning ensemble methods for anomaly detection in PLC-based ICS. The work presents two broad approaches to anomaly detection: a weighted voting ensemble approach with a learning algorithm based on coefficient of determination and a stacking-based ensemble approach using isolation forest met…
Purdue University（普渡大学）；Nanoelectronics Research Laboratory（纳米电子学研究实验室）
Stochastic gradient descent requires that training samples be drawn from a uniformly random distribution of the data. For a deployed system that must learn online from an uncontrolled and unknown environment, the ordering of input samples often fails to meet this criterion, making lifelong learning a difficult challenge. We exploit the locality of the unsupervised Spike Timing Dependent Plasticity (STDP) learning rule to target local representations in a Spiking Neural Network (SNN) to adapt to novel information while protecting essential information in the remainder of the SNN from catastroph…
Learning sensorimotor control policies from high-dimensional images crucially relies on the quality of the underlying visual representations. Prior works show that structured latent space such as visual keypoints often outperforms unstructured representations for robotic control. However, most of these representations, whether structured or unstructured are learned in a 2D space even though the control tasks are usually performed in a 3D environment. In this work, we propose a framework to learn such a 3D geometric structure directly from images in an end-to-end unsupervised manner. The input …
The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to learn object representations that are useful for control and reinforcement learning (RL). To this end, we introduce Transporter, a neural network architecture for discovering concise geometric object representations in terms of keypoints or image-space coordinates. Our method learns from raw video frames in a fully unsupervised manner, by transporting learnt ima…
University of California, Berkeley（加州大学伯克利分校）；OpenAI
Lagrangian methods are widely used algorithms for constrained optimization problems, but their learning dynamics exhibit oscillations and overshoot which, when applied to safe reinforcement learning, leads to constraint-violating behavior during agent training. We address this shortcoming by proposing a novel Lagrange multiplier update method that utilizes derivatives of the constraint function. We take a controls perspective, wherein the traditional Lagrange multiplier update behaves as \emph{integral} control; our terms introduce \emph{proportional} and \emph{derivative} control, achieving f…
Deep Reinforcement Learning (RL) has emerged as a powerful paradigm to solve a range of complex yet specific control tasks. Yet training generalist agents that can quickly adapt to new tasks remains an outstanding challenge. Recent advances in unsupervised RL have shown that pre-training RL agents with self-supervised intrinsic rewards can result in efficient adaptation. However, these algorithms have been hard to compare and develop due to the lack of a unified benchmark. To this end, we introduce the Unsupervised Reinforcement Learning Benchmark (URLB). URLB consists of two phases: reward-fr…
Customer support via chat requires agents to resolve customer queries with minimum wait time and maximum customer satisfaction. Given that the agents as well as the customers can have varying levels of literacy, the overall quality of responses provided by the agents tend to be poor if they are not predefined. But using only static responses can lead to customer detraction as the customers tend to feel that they are no longer interacting with a human. Hence, it is vital to have variations of the static responses to reduce monotonicity of the responses. However, maintaining a list of such varia…
We propose a model that is able to perform unsupervised physical parameter estimation of systems from video, where the differential equations governing the scene dynamics are known, but labeled states or objects are not available. Existing physical scene understanding methods require either object state supervision, or do not integrate with differentiable physics to learn interpretable system parameters and states. We address this problem through a physics-as-inverse-graphics approach that brings together vision-as-inverse-graphics and differentiable physics engines, enabling objects and expli…
In this work, we propose "global style tokens" (GSTs), a bank of embeddings that are jointly trained within Tacotron, a state-of-the-art end-to-end speech synthesis system. The embeddings are trained with no explicit labels, yet learn to model a large range of acoustic expressiveness. GSTs lead to a rich set of significant results. The soft interpretable "labels" they generate can be used to control synthesis in novel ways, such as varying speed and speaking style - independently of the text content. They can also be used for style transfer, replicating the speaking style of a single audio cli…
Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering. However, a central challenge in unsupervised RL is to extract behaviors that meaningfully affect the world and cover the range of possible outcomes, without getting distracted by inherently unpredictable, uncontrollable, and stochastic elements in the environment. To this end, we propose an unsupervised RL method designed for high-dimensional, stochastic environments based on an adversarial game between two policies (which we call Explore and…
