Reinforcement learning has shown great potential in developing high-level autonomous driving. However, for high-dimensional tasks, current RL methods suffer from low data efficiency and oscillation in the training process. This paper proposes an algorithm called Learn to drive with Virtual Memory (LVM) to overcome these problems. LVM compresses the high-dimensional information into compact latent states and learns a latent dynamic model to summarize the agent's experience. Various imagined latent trajectories are generated as virtual memory by the latent dynamic model. The policy is learned by propagating gradient through the learned latent model with the imagined latent trajectories and thus leads to high data efficiency. Furthermore, a double critic structure is designed to reduce the oscillation during the training process. The effectiveness of LVM is demonstrated by an image-input autonomous driving task, in which LVM outperforms the existing method in terms of data efficiency, learning stability, and control performance.

Multi-label classification (MLC) has recently received increasing interest from the machine learning community. Several studies provide reviews of methods and datasets for MLC and a few provide empirical comparisons of MLC methods. However, they are limited in the number of methods and datasets considered. This work provides a comprehensive empirical study of a wide range of MLC methods on a plethora of datasets from various domains. More specifically, our study evaluates 26 methods on 42 benchmark datasets using 20 evaluation measures. The adopted evaluation methodology adheres to the highest literature standards for designing and executing large scale, time-budgeted experimental studies. First, the methods are selected based on their usage by the community, assuring representation of methods across the MLC taxonomy of methods and different base learners. Second, the datasets cover a wide range of complexity and domains of application. The selected evaluation measures assess the predictive performance and the efficiency of the methods. The results of the analysis identify RFPCT, RFDTBR, ECCJ48, EBRJ48 and AdaBoostMH as best performing methods across the spectrum of performance measures. Whenever a new method is introduced, it should be compared to different subsets of MLC methods, determined on the basis of the different evaluation criteria.

Edge federated learning (FL) is an emerging machine learning paradigm that trains a global parametric model from distributed datasets via wireless communications. This paper proposes a unit-modulus over-the-air computation (UM-AirComp) framework to facilitate efficient edge federated learning, which simultaneously uploads local model parameters and updates global model parameters via analog beamforming. The proposed framework avoids sophisticated baseband signal processing, leading to low communication delays and implementation costs. A training loss bound of UM-AirComp is derived and two low-complexity algorithms, termed penalty alternating minimization (PAM) and accelerated gradient projection (AGP), are proposed to minimize the nonconvex nonsmooth loss bound. Simulation results show that the proposed UM-AirComp framework with PAM algorithm not only achieves a smaller mean square error of model parameters' estimation, training loss, and testing error, but also requires a significantly shorter runtime than that of other benchmark schemes. Moreover, the proposed UM-AirComp framework with AGP algorithm achieves satisfactory performance while reduces the computational complexity by orders of magnitude compared with existing optimization algorithms. Finally, we demonstrate the implementation of UM-AirComp in a vehicle-to-everything autonomous driving simulation platform. It is found that autonomous driving tasks are more sensitive to model parameter errors than other tasks since the former neural networks are more sophisticated containing sparser model parameters.

Title to be confirmed Speaker: Fabio Petroni Organised by: Stanford MLSys Join the email list to find out how to register for each seminar. Title to be confirmed Speaker: Chad Jenkins (University of Michigan) Organised by: Robotics Today Watch the seminar here. Title to be confirmed Speaker: Samory K. Kpotufe Organised by: London School of Economics and Political Science Register here.

In the study of natural and artificial complex systems, responses that are not completely determined by the considered decision variables are commonly modelled probabilistically, resulting in response distributions varying across decision space. We consider cases where the spatial variation of these response distributions does not only concern their mean and/or variance but also other features including for instance shape or uni-modality versus multi-modality. Our contributions build upon a non-parametric Bayesian approach to modelling the thereby induced fields of probability distributions, and in particular to a spatial extension of the logistic Gaussian model. The considered models deliver probabilistic predictions of response distributions at candidate points, allowing for instance to perform (approximate) posterior simulations of probability density functions, to jointly predict multiple moments and other functionals of target distributions, as well as to quantify the impact of collecting new samples on the state of knowledge of the distribution field of interest. In particular, we introduce adaptive sampling strategies leveraging the potential of the considered random distribution field models to guide system evaluations in a goal-oriented way, with a view towards parsimoniously addressing calibration and related problems from non-linear (stochastic) inversion and global optimisation.

Learning-from-demonstrations is an emerging paradigm to obtain effective robot control policies for complex tasks via reinforcement learning without the need to explicitly design reward functions. However, it is susceptible to imperfections in demonstrations and also raises concerns of safety and interpretability in the learned control policies. To address these issues, we use Signal Temporal Logic to evaluate and rank the quality of demonstrations. Temporal logic-based specifications allow us to create non-Markovian rewards, and also define interesting causal dependencies between tasks such as sequential task specifications. We validate our approach through experiments on discrete-world and OpenAI Gym environments, and show that our approach outperforms the state-of-the-art Maximum Causal Entropy Inverse Reinforcement Learning.

Graph Neural Networks (GNNs) have recently shown to be powerful tools for representing and analyzing graph data. So far GNNs is becoming an increasingly critical role in software engineering including program analysis, type inference, and code representation. In this paper, we introduce GraphGallery, a platform for fast benchmarking and easy development of GNNs based software. GraphGallery is an easy-to-use platform that allows developers to automatically deploy GNNs even with less domain-specific knowledge. It offers a set of implementations of common GNN models based on mainstream deep learning frameworks. In addition, existing GNNs toolboxes such as PyG and DGL can be easily incorporated into the platform. Experiments demonstrate the reliability of implementations and superiority in fast coding. The official source code of GraphGallery is available at https://github.com/EdisonLeeeee/GraphGallery and a demo video can be found at https://youtu.be/mv7Zs1YeaYo.

Understanding the principles of real-world biological multi-agent behaviors is a current challenge in various scientific and engineering fields. The rules regarding the real-world biological multi-agent behaviors such as team sports are often largely unknown due to their inherently higher-order interactions, cognition, and body dynamics. Estimation of the rules from data, i.e., data-driven approaches such as machine learning, provides an effective way for the analysis of such behaviors. Although most data-driven models have non-linear structures and high prediction performances, it is sometimes hard to interpret them. This survey focuses on data-driven analysis for quantitative understanding of invasion team sports behaviors such as basketball and football, and introduces two main approaches for understanding such multi-agent behaviors: (1) extracting easily interpretable features or rules from data and (2) generating and controlling behaviors in visually-understandable ways. The first approach involves the visualization of learned representations and the extraction of mathematical structures behind the behaviors. The second approach can be used to test hypotheses by simulating and controlling future and counterfactual behaviors. Lastly, the potential practical applications of extracted rules, features, and generated behaviors are discussed. These approaches can contribute to a better understanding of multi-agent behaviors in the real world.

Standard few-shot experiments involve learning to efficiently match previously unseen samples by class. We claim that few-shot learning should be long term, assimilating knowledge for the future, without forgetting previous concepts. In the mammalian brain, the hippocampus is understood to play a significant role in this process, by learning rapidly and consolidating knowledge to the neocortex over a short term period. In this research we tested whether an artificial hippocampal algorithm, AHA, could be used with a conventional ML model analogous to the neocortex, to achieve one-shot learning both short and long term. The results demonstrated that with the addition of AHA, the system could learn in one-shot and consolidate the knowledge for the long term without catastrophic forgetting. This study is one of the first examples of using a CLS model of hippocampus to consolidate memories, and it constitutes a step toward few-shot continual learning.

In this paper, we introduce a Model-based Algorithm Tuning Engine, namely MATE, where the parameters of an algorithm are represented as expressions of the features of a target optimisation problem. In contrast to most static (feature-independent) algorithm tuning engines such as irace and SPOT, our approach aims to derive the best parameter configuration of a given algorithm for a specific problem, exploiting the relationships between the algorithm parameters and the features of the problem. We formulate the problem of finding the relationships between the parameters and the problem features as a symbolic regression problem and we use genetic programming to extract these expressions in a human-readable form. For the evaluation, we apply our approach to the configuration of the (1 1) EA and RLS algorithms for the One-Max, LeadingOnes, BinValue and Jump optimisation problems, where the theoretically optimal algorithm parameters to the problems are available as functions of the features of the problems. Our study shows that the found relationships typically comply with known theoretical results - this demonstrates (1) the potential of model-based parameter tuning as an alternative to existing static algorithm tuning engines, and (2) its potential to discover relationships between algorithm performance and instance features in human-readable form.