Machine Learning
Relational Pooling for Graph Representations (1903.02541v1)
Ryan L. Murphy, Balasubramaniam Srinivasan, Vinayak Rao, Bruno Ribeiro
2019-03-06
This work generalizes graph neural networks (GNNs) beyond those based on the Weisfeiler-Lehman (WL) algorithm, graph Laplacians, and graph diffusion kernels. Our approach, denoted Relational Pooling (RP), draws from the theory of finite partial exchangeability to provide a framework with maximal representation power for graphs. RP can work with existing graph representation models, and somewhat counterintuitively, can make them even more powerful than the original WL isomorphism test. Additionally, RP is the first theoretically sound framework to use architectures like Recurrent Neural Networks and Convolutional Neural Networks for graph classification. RP also has graph kernels as a special case. We demonstrate improved performance of novel RP-based graph representations over current state-of-the-art methods on a number of tasks.
Autoregressive Convolutional Recurrent Neural Network for Univariate and Multivariate Time Series Prediction (1903.02540v1)
Matteo Maggiolo, Gerasimos Spanakis
2019-03-06
Time Series forecasting (univariate and multivariate) is a problem of high complexity due the different patterns that have to be detected in the input, ranging from high to low frequencies ones. In this paper we propose a new model for timeseries prediction that utilizes convolutional layers for feature extraction, a recurrent encoder and a linear autoregressive component. We motivate the model and we test and compare it against a baseline of widely used existing architectures for univariate and multivariate timeseries. The proposed model appears to outperform the baselines in almost every case of the multivariate timeseries datasets, in some cases even with 50% improvement which shows the strengths of such a hybrid architecture in complex timeseries.
Combining Optimal Control and Learning for Visual Navigation in Novel Environments (1903.02531v1)
Somil Bansal, Varun Tolani, Saurabh Gupta, Jitendra Malik, Claire Tomlin
2019-03-06
Model-based control is a popular paradigm for robot navigation because it can leverage a known dynamics model to efficiently plan robust robot trajectories. However, it is challenging to use model-based methods in settings where the environment is a priori unknown and can only be observed partially through on-board sensors on the robot. In this work, we address this short-coming by coupling model-based control with learning-based perception. The learning-based perception module produces a series of waypoints that guide the robot to the goal via a collision-free path. These waypoints are used by a model-based planner to generate a smooth and dynamically feasible trajectory that is executed on the physical system using feedback control. Our experiments in simulated real-world cluttered environments and on an actual ground vehicle demonstrate that the proposed approach can reach goal locations more reliably and efficiently in novel, previously-unknown environments as compared to a purely end-to-end learning-based alternative. Our approach is successfully able to exhibit goal-driven behavior without relying on detailed explicit 3D maps of the environment, works well with low frame rates, and generalizes well from simulation to the real world. Videos describing our approach and experiments are available on the project website.
Safety-Guided Deep Reinforcement Learning via Online Gaussian Process Estimation (1903.02526v1)
Jiameng Fan, Wenchao Li
2019-03-06
An important facet of reinforcement learning (RL) has to do with how the agent goes about exploring the environment. Traditional exploration strategies typically focus on efficiency and ignore safety. However, for practical applications, ensuring safety of the agent during exploration is crucial since performing an unsafe action or reaching an unsafe state could result in irreversible damage to the agent. The main challenge of safe exploration is that characterizing the unsafe states and actions is difficult for large continuous state or action spaces and unknown environments. In this paper, we propose a novel approach to incorporate estimations of safety to guide exploration and policy search in deep reinforcement learning. By using a cost function to capture trajectory-based safety, our key idea is to formulate the state-action value function of this safety cost as a candidate Lyapunov function and extend control-theoretic results to approximate its derivative using online Gaussian Process (GP) estimation. We show how to use these statistical models to guide the agent in unknown environments to obtain high-performance control policies with provable stability certificates.
Scaling up budgeted reinforcement learning (1903.01004v2)
Nicolas Carrara, Edouard Leurent, Romain Laroche, Tanguy Urvoy, Odalric-Ambrym Maillard, Olivier Pietquin
2019-03-03
Can we learn a control policy able to adapt its behaviour in real time so as to take any desired amount of risk? The general Reinforcement Learning framework solely aims at optimising a total reward in expectation, which may not be desirable in critical applications. In stark contrast, the Budgeted Markov Decision Process (BMDP) framework is a formalism in which the notion of risk is implemented as a hard constraint on a failure signal. Existing algorithms solving BMDPs rely on strong assumptions and have so far only been applied to toy-examples. In this work, we relax some of these assumptions and demonstrate the scalability of our approach on two practical problems: a spoken dialogue system and an autonomous driving task. On both examples, we reach similar performances as Lagrangian Relaxation methods with a significant improvement in sample and memory efficiency.
Learning multimodal representations for sample-efficient recognition of human actions (1903.02511v1)
Miguel Vasco, Francisco S. Melo, David Martins de Matos, Ana Paiva, Tetsunari Inamura
2019-03-06
Humans interact in rich and diverse ways with the environment. However, the representation of such behavior by artificial agents is often limited. In this work we present \textit{motion concepts}, a novel multimodal representation of human actions in a household environment. A motion concept encompasses a probabilistic description of the kinematics of the action along with its contextual background, namely the location and the objects held during the performance. Furthermore, we present Online Motion Concept Learning (OMCL), a new algorithm which learns novel motion concepts from action demonstrations and recognizes previously learned motion concepts. The algorithm is evaluated on a virtual-reality household environment with the presence of a human avatar. OMCL outperforms standard motion recognition algorithms on an one-shot recognition task, attesting to its potential for sample-efficient recognition of human actions.
Behavioural Repertoire via Generative Adversarial Policy Networks (1811.02945v2)
Marija Jegorova, Stéphane Doncieux, Timothy Hospedales
2018-11-07
Learning algorithms are enabling robots to solve increasingly challenging real-world tasks. These approaches often rely on demonstrations and reproduce the behavior shown. Unexpected changes in the environment may require using different behaviors to achieve the same effect, for instance to reach and grasp an object in changing clutter. An emerging paradigm addressing this robustness issue is to learn a diverse set of successful behaviors for a given task, from which a robot can select the most suitable policy when faced with a new environment. In this paper, we explore a novel realization of this vision by learning a generative model over policies. Rather than learning a single policy, or a small fixed repertoire, our generative model for policies compactly encodes an unbounded number of policies and allows novel controller variants to be sampled. Leveraging our generative policy network, a robot can sample novel behaviors until it finds one that works for a new environment. We demonstrate this idea with an application of robust ball-throwing in the presence of obstacles. We show that this approach achieves a greater diversity of behaviors than an existing evolutionary approach, while maintaining good efficacy of sampled behaviors, allowing a Baxter robot to hit targets more often when ball throwing in the presence of obstacles.
GQ-STN: Optimizing One-Shot Grasp Detection based on Robustness Classifier (1903.02489v1)
Alexandre Gariépy, Jean-Christophe Ruel, Brahim Chaib-draa, Philippe Giguère
2019-03-06
Grasping is a fundamental robotic task needed for the deployment of household robots or furthering warehouse automation. However, few approaches are able to perform grasp detection in real time (frame rate). To this effect, we present Grasp Quality Spatial Transformer Network (GQ-STN), a one-shot grasp detection network. Being based on the Spatial Transformer Network (STN), it produces not only a grasp configuration, but also directly outputs a depth image centered at this configuration. By connecting our architecture to an externally-trained grasp robustness evaluation network, we can train efficiently to satisfy a robustness metric via the backpropagation of the gradient emanating from the evaluation network. This removes the difficulty of training detection networks on sparsely annotated databases, a common issue in grasping. We further propose to use this robustness classifier to compare approaches, being more reliable than the traditional rectangle metric. Our GQ-STN is able to detect robust grasps on the depth images of the Dex-Net 2.0 dataset with 92.4 % accuracy in a single pass of the network. We finally demonstrate in a physical benchmark that our method can propose robust grasps more often than previous sampling-based methods, while being more than 60 times faster.
LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models (1903.02482v1)
Yuan Zhou, Bradley J. Gram-Hansen, Tobias Kohn, Tom Rainforth, Hongseok Yang, Frank Wood
2019-03-06
We develop a new Low-level, First-order Probabilistic Programming Language (LF-PPL) suited for models containing a mix of continuous, discrete, and/or piecewise-continuous variables. The key success of this language and its compilation scheme is in its ability to automatically distinguish parameters the density function is discontinuous with respect to, while further providing runtime checks for boundary crossings. This enables the introduction of new inference engines that are able to exploit gradient information, while remaining efficient for models which are not everywhere differentiable. We demonstrate this ability by incorporating a discontinuous Hamiltonian Monte Carlo (DHMC) inference engine that is able to deliver automated and efficient inference for non-differentiable models. Our system is backed up by a mathematical formalism that ensures that any model expressed in this language has a density with measure zero discontinuities to maintain the validity of the inference engine.
AIRD: Adversarial Learning Framework for Image Repurposing Detection (1903.00788v2)
Ayush Jaiswal, Yue Wu, Wael AbdAlmageed, Iacopo Masi, Premkumar Natarajan
2019-03-02
Image repurposing is a commonly used method for spreading misinformation on social media and online forums, which involves publishing untampered images with modified metadata to create rumors and further propaganda. While manual verification is possible, given vast amounts of verified knowledge available on the internet, the increasing prevalence and ease of this form of semantic manipulation call for the development of robust automatic ways of assessing the semantic integrity of multimedia data. In this paper, we present a novel method for image repurposing detection that is based on the real-world adversarial interplay between a bad actor who repurposes images with counterfeit metadata and a watchdog who verifies the semantic consistency between images and their accompanying metadata, where both players have access to a reference dataset of verified content, which they can use to achieve their goals. The proposed method exhibits state-of-the-art performance on location-identity, subject-identity and painting-artist verification, showing its efficacy across a diverse set of scenarios.