Latest in cs.ai

total 19764took 0.12s
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision ProcessesAug 22 2019Off-policy evaluation (OPE) in reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. We consider for the first time the semiparametric efficiency limits ... More
The double traveling salesman problem with partial last-in-first-out loading constraintsAug 22 2019In this paper, we introduce the Double Traveling Salesman Problem with Partial Last-In-First-Out Loading Constraints (DTSPPL), a pickup-and-delivery single-vehicle routing problem where all pickup operations must be performed before any delivery one because ... More
Simulation Model of Two-Robot Cooperation in Common Operating EnvironmentAug 22 2019The article considers a simulation modelling problem related to the chess game process occurring between two three-tier manipulators. The objective of the game construction lies in developing the procedure of effective control of the autonomous manipulator ... More
The many Shapley values for model explanationAug 22 2019The Shapley value has become a popular method to attribute the prediction of a machine-learning model on an input to its base features. The Shapley value [1] is known to be the unique method that satisfies certain desirable properties, and this motivates ... More
SCF2 -- an Argumentation Semantics for Rational Human Judgments on Argument Acceptability: Technical ReportAug 22 2019In abstract argumentation theory, many argumentation semantics have been proposed for evaluating argumentation frameworks. This paper is based on the following research question: Which semantics corresponds well to what humans consider a rational judgment ... More
The compositionality of neural networks: integrating symbolism and connectionismAug 22 2019Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally, a controversy that, in part, stems from a lack of agreement about what it means for a neural model to be compositional. ... More
Measuring the Business Value of Recommender SystemsAug 22 2019Recommender Systems are nowadays successfully used by all major web sites (from e-commerce to social media) to filter content and make suggestions in a personalized way. Academic research largely focuses on the value of recommenders for consumers, e.g., ... More
Report on the First Knowledge Graph Reasoning Challenge 2018 -- Toward the eXplainable AI SystemAug 22 2019A new challenge for knowledge graph reasoning started in 2018. Deep learning has promoted the application of artificial intelligence (AI) techniques to a wide variety of social problems. Accordingly, being able to explain the reason for an AI decision ... More
Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question AnsweringAug 22 2019BERT model has been successfully applied to open-domain QA tasks. However, previous work trains BERT by viewing passages corresponding to the same question as independent training instances, which may cause incomparable scores for answers from different ... More
A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy AdaptationAug 21 2019We introduce a new algorithm for multi-objective reinforcement learning (MORL) with linear preferences, with the goal of enabling few-shot adaptation to new tasks. In MORL, the aim is to learn policies over multiple competing objectives whose relative ... More
Design Space of Behaviour Planning for Autonomous DrivingAug 21 2019We explore the complex design space of behaviour planning for autonomous driving. Design choices that successfully address one aspect of behaviour planning can critically constrain others. To aid the design process, in this work we decompose the design ... More
Dialog State Tracking with Reinforced Data AugmentationAug 21 2019Neural dialog state trackers are generally limited due to the lack of quantity and diversity of annotated training data. In this paper, we address this difficulty by proposing a reinforcement learning (RL) based framework for data augmentation that can ... More
Technical Report on Implementing Ranking-Based Semantics in ConArgAug 21 2019ConArg is a suite of tools that offers a wide series of applications for dealing with argumentation problems. In this work, we present the advances we made in implementing a ranking-based semantics, based on computational choice power indexes, within ... More
Deep Reinforcement Learning for Foreign Exchange TradingAug 21 2019Reinforcement learning can interact with the environment and is suitable for applications in decision control systems. Therefore, we used the reinforcement learning method to establish a foreign exchange transaction, avoiding the long-standing problem ... More
P2L: Predicting Transfer Learning for Images and Semantic RelationsAug 20 2019Transfer learning enhances learning across tasks, by leveraging previously learned representations -- if they are properly chosen. We describe an efficient method to accurately estimate the appropriateness of a previously trained model for use in a new ... More
Reinforcement Learning is not a Causal problemAug 20 2019We use an analogy between non-isomorphic mathematical structures defined over the same set and the algebras induced by associative and causal levels of information in order to argue that Reinforcement Learning, in its current formulation, is not a causal ... More
Developing Creative AI to Generate Sculptural ObjectsAug 20 2019We explore the intersection of human and machine creativity by generating sculptural objects through machine learning. This research raises questions about both the technical details of automatic art generation and the interaction between AI and people, ... More
Playing magic tricks to deep neural networks untangles human deceptionAug 20 2019Magic is the art of producing in the spectator an illusion of impossibility. Although the scientific study of magic is in its infancy, the advent of recent tracking algorithms based on deep learning allow now to quantify the skills of the magician in ... More
Accurate and interpretable evaluation of surgical skills from kinematic data using fully convolutional neural networksAug 20 2019Purpose: Manual feedback from senior surgeons observing less experienced trainees is a laborious task that is very expensive, time-consuming and prone to subjectivity. With the number of surgical procedures increasing annually, there is an unprecedented ... More
Unsupervised Hierarchical Grouping of Knowledge Graph EntitiesAug 20 2019Knowledge graphs have attracted lots of attention in academic and industrial environments. Despite their usefulness, popular knowledge graphs suffer from incompleteness of information, especially in their type assertions. This has encouraged research ... More
An Expert System Approach for determine the stage of UiTM Perlis Palapes Cadet Performance and Ranking SelectionAug 20 2019The palapes cadets are one of the uniform organizations in UiTM Perlis for extra-curricular activities. The palapes cadets arrange their organization in a hierarchy according to grade. Senior uniform officer (SUO) is the highest rank, followed by a junior ... More
LogicENN: A Neural Based Knowledge Graphs Embedding Model with Logical RulesAug 20 2019Knowledge graph embedding models have gained significant attention in AI research. Recent works have shown that the inclusion of background knowledge, such as logical rules, can improve the performance of embeddings in downstream machine learning tasks. ... More
Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge AmalgamationAug 20 2019A massive number of well-trained deep networks have been released by developers online. These networks may focus on different tasks and in many cases are optimized for different datasets. In this paper, we study how to exploit such heterogeneous pre-trained ... More
Learning from failures in robot-assisted feeding: Using online learning to develop manipulation strategies for bite acquisitionAug 19 2019Successful robot-assisted feeding requires bite acquisition of a wide variety of food items. Different food items may require different manipulation actions for successful bite acquisition. Therefore, a key challenge is to handle previously-unseen food ... More
Domain-Independent turn-level Dialogue Quality Evaluation via User Satisfaction EstimationAug 19 2019An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate user satisfaction ... More
It Takes Nine to Smell a Rat: Neural Multi-Task Learning for Check-Worthiness PredictionAug 19 2019We propose a multi-task deep-learning approach for estimating the check-worthiness of claims in political debates. Given a political debate, such as the 2016 US Presidential and Vice-Presidential ones, the task is to predict which statements in the debate ... More
Evaluating Hierarchies through A Partially Observable Markov Decision Processes MethodologyAug 19 2019Hierarchical clustering has been shown to be valuable in many scenarios, e.g. catalogues, biology research, image processing, and so on. Despite its usefulness to many situations, there is no agreed methodology on how to properly evaluate the hierarchies ... More
Implications of Quantum Computing for Artificial Intelligence alignment researchAug 19 2019We introduce a heuristic model of Quantum Computing and apply it to argue that a deep understanding of quantum computing is unlikely to be helpful to address current bottlenecks in Artificial Intelligence Alignment. Our argument relies on the claims that ... More
A novel text representation which enables image classifiers to perform text classification, applied to name disambiguationAug 19 2019Patent data are often used to study the process of innovation and research, but patent databases lack unique identifiers for individual inventors, making it difficult to study innovation processes at the individual level. Here we introduce an algorithm ... More
Message Passing for Complex Question Answering over Knowledge GraphsAug 19 2019Question answering over knowledge graphs (KGQA) has evolved from simple single-fact questions to complex questions that require graph traversal and aggregation. We propose a novel approach for complex KGQA that uses unsupervised message passing, which ... More
A survey on intrinsic motivation in reinforcement learningAug 19 2019Despite numerous research work in reinforcement learning (RL) and the recent successes obtained by combining it with deep learning, deep reinforcement learning (DRL) is still facing many challenges. Some of them, like the ability to abstract actions or ... More
An Autonomous Performance Testing Framework using Self-Adaptive Fuzzy Reinforcement LearningAug 19 2019Test automation can result in reduction in cost and human effort. If the optimal policy, the course of actions taken, for the intended objective in a testing process could be learnt by the testing system (e.g., a smart tester agent), then it could be ... More
Computational Flight Control: A Domain-Knowledge-Aided Deep Reinforcement Learning ApproachAug 19 2019This papers aims to examine the potential of using the emerging deep reinforcement learning techniques in flight control. Instead of learning from scratch, the autopilot structure is fixed as typical three-loop autopilot and deep reinforcement learning ... More
Efficient Discovery of Expressive Multi-label Rules using Relaxed PruningAug 19 2019Being able to model correlations between labels is considered crucial in multi-label classification. Rule-based models enable to expose such dependencies, e.g., implications, subsumptions, or exclusions, in an interpretable and human-comprehensible manner. ... More
Are You for Real? Detecting Identity Fraud via Dialogue InteractionsAug 19 2019Identity fraud detection is of great importance in many real-world scenarios such as the financial industry. However, few studies addressed this problem before. In this paper, we focus on identity fraud detection in loan applications and propose to solve ... More
Towards Assessing the Impact of Bayesian Optimization's Own HyperparametersAug 19 2019Bayesian Optimization (BO) is a common approach for hyperparameter optimization (HPO) in automated machine learning. Although it is well-accepted that HPO is crucial to obtain well-performing machine learning models, tuning BO's own hyperparameters is ... More
Reinforcement Learning ApplicationsAug 19 2019We start with a brief introduction to reinforcement learning (RL), about its successful stories, basics, an example, issues, the ICML 2019 Workshop on RL for Real Life, how to use it, study material and an outlook. Then we discuss a selection of RL applications, ... More
Intrinsically Motivated Exploration for Automated Discovery of Patterns in Morphogenetic SystemsAug 19 2019Exploration is a cornerstone both for machine learning algorithms and for science in general to discover novel solutions, phenomena and behaviors. Intrinsically motivated goal exploration processes (IMGEPs) were shown to enable autonomous agents to efficiently ... More
Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human DataAug 19 2019Deep neural networks have been successfully applied in learning the board games Go, chess and shogi without prior knowledge by making use of reinforcement learning. Although starting from zero knowledge has been shown to yield impressive results, it is ... More
Transfer in Deep Reinforcement Learning using Knowledge GraphsAug 19 2019Text adventure games, in which players must make sense of the world through text descriptions and declare actions through text descriptions, provide a stepping stone toward grounding action in language. Prior work has demonstrated that using a knowledge ... More
Assessing the Safety and Reliability of Autonomous Vehicles from Road TestingAug 19 2019There is an urgent societal need to assess whether autonomous vehicles (AVs) are safe enough. From published quantitative safety and reliability assessments of AVs, we know that, given the goal of predicting very low rates of accidents, road testing alone ... More
RefNet: A Reference-aware Network for Background Based ConversationAug 18 2019Existing conversational systems tend to generate generic responses. Recently, Background Based Conversations (BBCs) have been introduced to address this issue. Here, the generated responses are grounded in some background information. The proposed methods ... More
Music Transcription Based on Bayesian Piece-Specific Score Models Capturing RepetitionsAug 18 2019Most work on models for music transcription has focused on describing local sequential dependence of notes in musical scores and failed to capture their global repetitive structure, which can be a useful guide for transcribing music. Focusing on the rhythm, ... More
A Multi-level Neural Network for Implicit Causality Detection in Web TextsAug 18 2019Mining causality from text is a complex and crucial natural language understanding task. Most of the early attempts at its solution can group into two categories: 1) utilizing co-occurrence frequency and world knowledge for causality detection; 2) extracting ... More
Understanding Cyber Athletes Behaviour Through a Smart Chair: CS:GO and Monolith Team ScenarioAug 18 2019eSports is the rapidly developing multidisciplinary domain. However, research and experimentation in eSports are in the infancy. In this work, we propose a smart chair platform - an unobtrusive approach to the collection of data on the eSports athletes ... More
eSports Pro-Players Behavior During the Game Events: Statistical Analysis of Data Obtained Using the Smart ChairAug 18 2019Today's competition between the professional eSports teams is so strong that in-depth analysis of players' performance literally crucial for creating a powerful team. There are two main approaches to such an estimation: obtaining features and metrics ... More
VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual NavigationAug 18 2019In this paper, we show how novel transfer reinforcement learning techniques can be applied to the complex task of target driven navigation using the photorealistic AI2THOR simulator. Specifically, we build on the concept of Universal Successor Features ... More
What is needed for simple spatial language capabilities in VQA?Aug 17 2019Visual question answering (VQA) comprises a variety of language capabilities. The diagnostic benchmark dataset CLEVR has fueled progress by helping to better assess and distinguish models in basic abilities like counting, comparing and spatial reasoning ... More
Prune Sampling: a MCMC inference technique for discrete and deterministic Bayesian networksAug 17 2019We introduce and characterise the performance of the Markov chain Monte Carlo (MCMC) inference method Prune Sampling for discrete and deterministic Bayesian networks (BNs). We developed a procedure to obtain the performance of a MCMC sampling method in ... More
Search Algorithms for MastermindAug 16 2019his paper presents two novel approaches to solving the classic board game mastermind, including a variant of simulated annealing (SA) and a technique we term maximum expected reduction in consistency (MERC). In addition, we compare search results for ... More
Multi-View Broad Learning System for Primate Oculomotor Decision DecodingAug 16 2019Multi-view learning improves the learning performance by utilizing multi-view data: data collected from multiple sources, or feature sets extracted from the same data source. This approach is suitable for primate brain state decoding using cortical neural ... More
Distributional Negative Sampling for Knowledge Base CompletionAug 16 2019State-of-the-art approaches for Knowledge Base Completion (KBC) exploit deep neural networks trained with both false and true assertions: positive assertions are explicitly taken from the knowledge base, whereas negative ones are generated by random sampling ... More
Learning Representations and Agents for Information RetrievalAug 16 2019A goal shared by artificial intelligence and information retrieval is to create an oracle, that is, a machine that can answer our questions, no matter how difficult they are. A more limited, but still instrumental, version of this oracle is a question-answering ... More
Continuous Relaxation of Symbolic Planner for One-Shot Imitation LearningAug 16 2019We address one-shot imitation learning, where the goal is to execute a previously unseen task based on a single demonstration. While there has been exciting progress in this direction, most of the approaches still require a few hundred tasks for meta-training, ... More
Performing Deep Recurrent Double Q-Learning for Atari GamesAug 16 2019Currently, many applications in Machine Learning are based on define new models to extract more information about data, In this case Deep Reinforcement Learning with the most common application in video games like Atari, Mario, and others causes an impact ... More
Exploring Properties of Icosoku by Constraint Satisfaction ApproachAug 16 2019Icosoku is a challenging and interesting puzzle that exhibits highly symmetrical and combinatorial nature. In this paper, we pose the questions derived from the puzzle, but with more difficulty and generality. In addition, we also present a constraint ... More
BOAH: A Tool Suite for Multi-Fidelity Bayesian Optimization & Analysis of HyperparametersAug 16 2019Hyperparameter optimization and neural architecture search can become prohibitively expensive for regular black-box Bayesian optimization because the training and evaluation of a single model can easily take several hours. To overcome this, we introduce ... More
The Regularization of Small Sub-Constraint Satisfaction ProblemsAug 16 2019This paper describes a new approach on optimization of constraint satisfaction problems (CSPs) by means of substituting sub-CSPs with locally consistent regular membership constraints. The purpose of this approach is to reduce the number of fails in the ... More
Iterative Update and Unified Representation for Multi-Agent Reinforcement LearningAug 16 2019Multi-agent systems have a wide range of applications in cooperative and competitive tasks. As the number of agents increases, nonstationarity gets more serious in multi-agent reinforcement learning (MARL), which brings great difficulties to the learning ... More
Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based ChatbotsAug 16 2019This paper proposes a dually interactive matching network (DIM) for presenting the personalities of dialogue agents in retrieval-based chatbots. This model develops from the interactive matching network (IMN) which models the matching degree between a ... More
Natural Language Processing of Clinical Notes on Chronic Diseases: Systematic ReviewAug 15 2019Of the 2652 articles considered, 106 met the inclusion criteria. Review of the included papers resulted in identification of 43 chronic diseases, which were then further classified into 10 disease categories using ICD-10. The majority of studies focused ... More
Examining the Use of Temporal-Difference Incremental Delta-Bar-Delta for Real-World Predictive Knowledge ArchitecturesAug 15 2019Predictions and predictive knowledge have seen recent success in improving not only robot control but also other applications ranging from industrial process control to rehabilitation. A property that makes these predictive approaches well suited for ... More
PHYRE: A New Benchmark for Physical ReasoningAug 15 2019Understanding and reasoning about physics is an important ability of intelligent agents. We develop the PHYRE benchmark for physical reasoning that contains a set of simple classical mechanics puzzles in a 2D physical environment. The benchmark is designed ... More
Tracing Player Knowledge in a Parallel Programming Educational GameAug 15 2019This paper focuses on "tracing player knowledge" in educational games. Specifically, given a set of concepts or skills required to master a game, the goal is to estimate the likelihood with which the current player has mastery of each of those concepts ... More
Conditional LSTM-GAN for Melody Generation from LyricsAug 15 2019Melody generation from lyrics has been a challenging research issue in the field of artificial intelligence and music, which enables to learn and discover latent relationship between interesting lyrics and accompanying melody. Unfortunately, the limited ... More
A Multivariate Model for Representing Semantic Non-compositionalityAug 15 2019Semantically non-compositional phrases constitute an intriguing research topic in Natural Language Processing. Semantic non-compositionality --the situation when the meaning of a phrase cannot be derived from the meaning of its components, is the main ... More
Playing a Strategy Game with Knowledge-Based Reinforcement LearningAug 15 2019This paper presents Knowledge-Based Reinforcement Learning (KB-RL) as a method that combines a knowledge-based approach and a reinforcement learning (RL) technique into one method for intelligent problem solving. The proposed approach focuses on multi-expert ... More
Multi-class Hierarchical Question Classification for Multiple Choice Science ExamsAug 15 2019Prior work has demonstrated that question classification (QC), recognizing the problem domain of a question, can help answer it more accurately. However, developing strong QC algorithms has been hindered by the limited size and complexity of annotated ... More
Model-based Lookahead Reinforcement LearningAug 15 2019Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics. However, despite the impressive data-efficiency, MBRL does not achieve the final performance of state-of-the-art Model-free ... More
Evaluating Empathy in Artificial AgentsAug 14 2019The novel research area of computational empathy is in its infancy and moving towards developing methods and standards. One major problem is the lack of agreement on the evaluation of empathy in artificial interactive systems. Even though the existence ... More
Continuous Control for High-Dimensional State Spaces: An Interactive Learning ApproachAug 14 2019Deep Reinforcement Learning (DRL) has become a powerful methodology to solve complex decision-making problems. However, DRL has several limitations when used in real-world problems (e.g., robotics applications). For instance, long training times are required ... More
Toward a Dempster-Shafer theory of conceptsAug 14 2019In this paper, we generalize the basic notions and results of Dempster-Shafer theory from predicates to formal concepts. Results include the representation of conceptual belief functions as inner measures of suitable probability functions, and a Dempster-Shafer ... More
Mastering emergent language: learning to guide in simulated navigationAug 14 2019To cooperate with humans effectively, virtual agents need to be able to understand and execute language instructions. A typical setup to achieve this is with a scripted teacher which guides a virtual agent using language instructions. However, such setup ... More
FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine ComprehensionAug 14 2019Conversational machine comprehension requires deep understanding of the dialogue flow, and the prior work proposed FlowQA to implicitly model the context representations in reasoning for better understanding. This paper proposes to explicitly model the ... More
Unsupervised Behavior Change Detection in Multidimensional Data Streams for Maritime Traffic MonitoringAug 14 2019The worldwide growth of maritime traffic and the development of the Automatic Identification System (AIS) has led to advances in monitoring systems for preventing vessel accidents and detecting illegal activities. In this work, we describe research gaps ... More
Towards Linearization Machine Learning AlgorithmsAug 14 2019This paper is about a machine learning approach based on the multilinear projection of an unknown function (or probability distribution) to be estimated towards a linear (or multilinear) dimensional space E'. The proposal transforms the problem of predicting ... More
Towards Explainable AI Planning as a ServiceAug 14 2019Explainable AI is an important area of research within which Explainable Planning is an emerging topic. In this paper, we argue that Explainable Planning can be designed as a service -- that is, as a wrapper around an existing planning system that utilises ... More
VideoNavQA: Bridging the Gap between Visual and Embodied Question AnsweringAug 14 2019Embodied Question Answering (EQA) is a recently proposed task, where an agent is placed in a rich 3D environment and must act based solely on its egocentric input to answer a given question. The desired outcome is that the agent learns to combine capabilities ... More
Reasoning-Driven Question-Answering for Natural Language UnderstandingAug 14 2019Natural language understanding (NLU) of text is a fundamental challenge in AI, and it has received significant attention throughout the history of NLP research. This primary goal has been studied under different tasks, such as Question Answering (QA) ... More
HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base CompletionAug 14 2019Learning embeddings of entities and relations existing in knowledge bases allows the discovery of hidden patterns not captured in the original data. In this paper, we propose a novel embedding model, dubbed HyperKG, for knowledge base completion. Our ... More
Local Score Dependent Model Explanation for Time Dependent CovariatesAug 13 2019The use of deep neural networks to make high risk decisions creates a need for global and local explanations so that users and experts have confidence in the modeling algorithms. We introduce a novel technique to find global and local explanations for ... More
Learn How to Cook a New Recipe in a New House: Using Map Familiarization, Curriculum Learning, and Common Sense to Learn Families of Text-Based Adventure GamesAug 13 2019We consider the task of learning to play families of text-based computer adventure games, i.e., fully textual environments with a common theme (e.g. cooking) and goal (e.g. prepare a meal from a recipe) but with different specifics; new instances of such ... More
Fine-grained Information Status Classification Using Discourse Context-Aware Self-AttentionAug 13 2019Previous work on bridging anaphora recognition (Hou et al., 2013a) casts the problem as a subtask of learning fine-grained information status (IS). However, these systems heavily depend on many hand-crafted linguistic features. In this paper, we propose ... More
Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram PerspectiveAug 13 2019Can an arbitrarily intelligent reinforcement learning agent be kept under control by a human user? Or do agents with sufficient intelligence inevitably find ways to shortcut their reward signal? This question impacts how far reinforcement learning can ... More
Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram PerspectiveAug 13 2019Aug 15 2019Can an arbitrarily intelligent reinforcement learning agent be kept under control by a human user? Or do agents with sufficient intelligence inevitably find ways to shortcut their reward signal? This question impacts how far reinforcement learning can ... More
Semi-Supervised Learning using Differentiable ReasoningAug 13 2019We introduce Differentiable Reasoning (DR), a novel semi-supervised learning technique which uses relational background knowledge to benefit from unlabeled data. We apply it to the Semantic Image Interpretation (SII) task and show that background knowledge ... More
Inverse Rational Control with Partially Observable Continuous Nonlinear DynamicsAug 13 2019Continuous control and planning remains a major challenge in robotics and machine learning. Neuroscience offers the possibility of learning from animal brains that implement highly successful controllers, but it is unclear how to relate an animal's behavior ... More
Multi-Agent Manipulation via Locomotion using Hierarchical Sim2RealAug 13 2019Manipulation and locomotion are closely related problems that are often studied in isolation. In this work, we study the problem of coordinating multiple mobile agents to exhibit manipulation behaviors using a reinforcement learning (RL) approach. Our ... More
Is Deep Reinforcement Learning Really Superhuman on Atari?Aug 13 2019Consistent and reproducible evaluation of Deep Reinforcement Learning (DRL) is not straightforward. In the Arcade Learning Environment (ALE), small changes in environment parameters such as stochasticity or the maximum allowed play time can lead to very ... More
Variational Fusion for Multimodal Sentiment AnalysisAug 13 2019Multimodal fusion is considered a key step in multimodal tasks such as sentiment analysis, emotion detection, question answering, and others. Most of the recent work on multimodal fusion does not guarantee the fidelity of the multimodal representation ... More
Evaluation of a Recommender System for Assisting Novice Game DesignersAug 13 2019Game development is a complex task involving multiple disciplines and technologies. Developers and researchers alike have suggested that AI-driven game design assistants may improve developer workflow. We present a recommender system for assisting humans ... More
Getting To Know You: User Attribute Extraction from DialoguesAug 13 2019User attributes provide rich and useful information for user understanding, yet structured and easy-to-use attributes are often sparsely populated. In this paper, we leverage dialogues with conversational agents, which contain strong suggestions of user ... More
Competitive Multi-Agent Deep Reinforcement Learning with Counterfactual ThinkingAug 13 2019Aug 16 2019Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to perform better in ... More
Competitive Multi-Agent Deep Reinforcement Learning with Counterfactual ThinkingAug 13 2019Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to perform better in ... More
Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian ModelAug 13 2019In this paper we introduce the ice-start problem, i.e., the challenge of deploying machine learning models when only little or no training data is initially available, and acquiring each feature element of data is associated with costs. This setting is ... More
Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian ModelAug 13 2019Aug 14 2019In this paper we introduce the ice-start problem, i.e., the challenge of deploying machine learning models when only little or no training data is initially available, and acquiring each feature element of data is associated with costs. This setting is ... More
From Crystallized Adaptivity to Fluid Adaptivity in Deep Reinforcement Learning -- Insights from Biological Systems on Adaptive FlexibilityAug 13 2019Recent developments in machine-learning algorithms have led to impressive performance increases in many traditional application scenarios of artificial intelligence research. In the area of deep reinforcement learning, deep learning functional architectures ... More
Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA SystemAug 13 2019In real-world question-answering (QA) systems, ill-formed questions, such as wrong words, ill word order, and noisy expressions, are common and may prevent the QA systems from understanding and answering them accurately. In order to eliminate the effect ... More
Reinforcement Learning based Interconnection Routing for Adaptive Traffic OptimizationAug 13 2019Applying Machine Learning (ML) techniques to design and optimize computer architectures is a promising research direction. Optimizing the runtime performance of a Network-on-Chip (NoC) necessitates a continuous learning framework. In this work, we demonstrate ... More
Building a Massive Corpus for Named Entity Recognition using Free Open Data SourcesAug 13 2019With the recent progress in machine learning, boosted by techniques such as deep learning, many tasks can be successfully solved once a large enough dataset is available for training. Nonetheless, human-annotated datasets are often expensive to produce, ... More