We study the problem of efficient exploration in order to learn an accurate model of an environment, modeled as a Markov decision process (MDP). Efficient exploration in this problem requires the agent to identify the regions in which estimating the model is more difficult and then exploit this knowledge to collect more samples there. In this paper, we formalize this problem, introduce the first algorithm to learn an $\epsilon$-accurate estimate of the dynamics, and provide its sample complexity analysis. While this algorithm enjoys strong guarantees in the large-sample regime, it tends to have a poor performance in early stages of exploration. To address this issue, we propose an algorithm that is based on maximum weighted entropy, a heuristic that stems from common sense and our theoretical analysis. The main idea here is cover the entire state-action space with the weight proportional to the noise in the transitions. Using a number of simple domains with heterogeneous noise in their transitions, we show that our heuristic-based algorithm outperforms both our original algorithm and the maximum entropy algorithm in the small sample regime, while achieving similar asymptotic performance as that of the original algorithm.

There has been a surge of interest in continual learning and federated learning, both of which are important in training deep neural networks in real-world scenarios. Yet little research has been done regarding the scenario where each client learns on a sequence of tasks from private local data. This problem of federated continual learning poses new challenges to continual learning, such as utilizing knowledge and preventing interference from tasks learned on other clients. To resolve these issues, we propose a novel federated continual learning framework, Federated continual learning with Adaptive Parameter Communication, which additively decomposes the network weights into global shared parameters and sparse task-specific parameters. This decomposition allows to minimize interference between incompatible tasks, and also allows inter-client knowledge transfer by communicating the sparse task-specific parameters. Our federated continual learning framework is also communication-efficient, due to high sparsity of the parameters and sparse parameter update. We validate APC against existing federated learning and local continual learning methods under varying degrees of task similarity across clients, and show that our model significantly outperforms them with a large reduction in the communication cost.

We describe nearly fifteen years of General Game Playing experimental research history in the context of reproducibility and fairness of comparisons between various GGP agents and systems designed to play games described by different formalisms. We think our survey may provide an interesting perspective of how chaotic methods were allowed when nothing better was possible. Finally, from our experience-based view, we would like to propose a few recommendations of how such specific heterogeneous branch of research should be handled appropriately in the future. The goal of this note is to point out common difficulties and problems in the experimental research in the area. We hope that our recommendations will help in avoiding them in future works and allow more fair and reproducible comparisons.

Precise trajectory prediction of surrounding vehicles is critical for decision-making of autonomous vehicles and learning-based approaches are well recognized for the robustness. However, state-of-the-art learning-based methods ignore 1) the feasibility of the vehicle's multi-modal state information for prediction and 2) the mutual exclusive relationship between the global traffic scene receptive fields and the local position resolution when modeling vehicles' interactions, which may influence prediction accuracy. Therefore, we propose a vehicle-descriptor based LSTM model with the dilated convolutional social pooling (VD+DCS-LSTM) to cope with the above issues. First, each vehicle's multi-modal state information is employed as our model's input and a new vehicle descriptor encoded by stacked sparse auto-encoders is proposed to reflect the deep interactive relationships between various states, achieving the optimal feature extraction and effective use of multi-modal inputs. Secondly, the LSTM encoder is used to encode the historical sequences composed of the vehicle descriptor and a novel dilated convolutional social pooling is proposed to improve modeling vehicles' spatial interactions. Thirdly, the LSTM decoder is used to predict the probability distribution of future trajectories based on maneuvers. The validity of the overall model was verified over the NGSIM US-101 and I-80 datasets and our method outperforms the latest benchmark.

Organize songs, albums, and artists in groups with shared similarity could be done with the help of genre labels. In this paper, we present a novel approach for automatic classifying musical genre in Brazilian music using only the song lyrics. This kind of classification remains a challenge in the field of Natural Language Processing. We construct a dataset of 138,368 Brazilian song lyrics distributed in 14 genres. We apply SVM, Random Forest and a Bidirectional Long Short-Term Memory (BLSTM) network combined with different word embeddings techniques to address this classification task. Our experiments show that the BLSTM method outperforms the other models with an F1-score average of $0.48$. Some genres like "gospel", "funk-carioca" and "sertanejo", which obtained 0.89, 0.70 and 0.69 of F1-score, respectively, can be defined as the most distinct and easy to classify in the Brazilian musical genres context.

Increasing the autonomy level of a robot hand to accomplish remote object manipulation tasks faster and easier is a new and promising topic in teleoperation. Such semi-autonomous telemanipulation, however, is very challenging due to the physical discrepancy between the human hand and the robot hand, along with the fine motion constraints required for the manipulation task. To overcome these challenges, the robot needs to learn how to assist the human operator in a preferred/intuitive way, which must provide effective assistance that the operator needs yet still accommodate human inputs, so the operator feels in control of the system (i.e., not counter-intuitive to the operator). Toward this goal, we develop novel data-driven approaches to stably learn what assistance is preferred from high data variance caused by the ambiguous nature of human operators. To avoid an extensive robot-specific training process, methods to transfer this assistance knowledge between different robot hands are discussed. Experiments were conducted to telemanipulate a cup for three principal tasks: usage, move, and handover by remotely controlling a 3-finger gripper and 2-finger gripper. Results demonstrated that the proposed model effectively learned the knowledge of preferred assistance, and knowledge transfer between robots allows this semi-autonomous telemanipulation strategy to be scaled up with less training efforts.

We design a new technique for the distributional semantic modeling with a neural network-based approach to learn distributed term representations (or term embeddings) - term vector space models as a result, inspired by the recent ontology-related approach (using different types of contextual knowledge such as syntactic knowledge, terminological knowledge, semantic knowledge, etc.) to the identification of terms (term extraction) and relations between them (relation extraction) called semantic pre-processing technology - SPT. Our method relies on automatic term extraction from the natural language texts and subsequent formation of the problem-oriented or application-oriented (also deeply annotated) text corpora where the fundamental entity is the term (includes non-compositional and compositional terms). This gives us an opportunity to changeover from distributed word representations (or word embeddings) to distributed term representations (or term embeddings). This transition will allow to generate more accurate semantic maps of different subject domains (also, of relations between input terms - it is useful to explore clusters and oppositions, or to test your hypotheses about them). The semantic map can be represented as a graph using Vec2graph - a Python library for visualizing word embeddings (term embeddings in our case) as dynamic and interactive graphs. The Vec2graph library coupled with term embeddings will not only improve accuracy in solving standard NLP tasks, but also update the conventional concept of automated ontology development. The main practical result of our work is the development kit (set of toolkits represented as web service APIs and web application), which provides all necessary routines for the basic linguistic pre-processing and the semantic pre-processing of the natural language texts in Ukrainian for future training of term vector space models.

This paper presents the Designer Preference Model, a data-driven solution that pursues to learn from user generated data in a Quality-Diversity Mixed-Initiative Co-Creativity (QD MI-CC) tool, with the aims of modelling the user's design style to better assess the tool's procedurally generated content with respect to that user's preferences. Through this approach, we aim for increasing the user's agency over the generated content in a way that neither stalls the user-tool reciprocal stimuli loop nor fatigues the user with periodical suggestion handpicking. We describe the details of this novel solution, as well as its implementation in the MI-CC tool the Evolutionary Dungeon Designer. We present and discuss our findings out of the initial tests carried out, spotting the open challenges for this combined line of research that integrates MI-CC with Procedural Content Generation through Machine Learning.

Many current behavior generation methods struggle to handle real-world traffic situations as they do not scale well with complexity. However, behaviors can be learned off-line using data-driven approaches. Especially, reinforcement learning is promising as it implicitly learns how to behave utilizing collected experiences. In this work, we combine policy-based reinforcement learning with local optimization to foster and synthesize the best of the two methodologies. The policy-based reinforcement learning algorithm provides an initial solution and guiding reference for the post-optimization. Therefore, the optimizer only has to compute a single homotopy class, e.g.\ drive behind or in front of the other vehicle. By storing the state-history during reinforcement learning, it can be used for constraint checking and the optimizer can account for interactions. The post-optimization additionally acts as a safety-layer and the novel method, thus, can be applied in safety-critical applications. We evaluate the proposed method using lane-change scenarios with a varying number of vehicles.

Neural network pruning---the task of reducing the size of a network by removing parameters---has been the subject of a great deal of work in recent years. We provide a meta-analysis of the literature, including an overview of approaches to pruning and consistent findings in the literature. After aggregating results across 81 papers and pruning hundreds of models in controlled conditions, our clearest finding is that the community suffers from a lack of standardized benchmarks and metrics. This deficiency is substantial enough that it is hard to compare pruning techniques to one another or determine how much progress the field has made over the past three decades. To address this situation, we identify issues with current practices, suggest concrete remedies, and introduce ShrinkBench, an open-source framework to facilitate standardized evaluations of pruning methods. We use ShrinkBench to compare various pruning techniques and show that its comprehensive evaluation can prevent common pitfalls when comparing pruning methods.