• arXiv.cs.AI Pub Date : 2020-07-06
Gabriel K. Sepulveda; Felipe Besoain; Nicolas A. Barriga

Videogames are nowadays one of the biggest entertainment industries in the world. Being part of this industry means competing against lots of other companies and developers, thus, making fanbases of vital importance. They are a group of clients that constantly support your company because your video games are fun. Videogames are most entertaining when the difficulty level is a good match for the player's

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-11
Hao Liu; Ying Li; Yanjie Fu; Huaibo Mei; Jingbo Zhou; Xu Ma; Hui Xiong

Public transportation plays a critical role in people's daily life. It has been proven that public transportation is more environmentally sustainable, efficient, and economical than any other forms of travel. However, due to the increasing expansion of transportation networks and more complex travel situations, people are having difficulties in efficiently finding the most preferred route from one

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Tineke Blom; Mirthe M. van Diepen; Joris M. Mooij

Real-world systems are often modelled by sets of equations with exogenous random variables. What can we say about the probabilistic and causal aspects of variables that appear in these equations without explicitly solving for them? We prove that, under a solvability assumption, we can construct a Markov ordering graph that implies conditional independences and a causal ordering graph that encodes the

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Natalia Criado; Xavier Ferrer; Jose M. Such

Digital discrimination is a form of discrimination whereby users are automatically treated unfairly, unethically or just differently based on their personal data by a machine learning (ML) system. Examples of digital discrimination include low-income neighbourhood's targeted with high-interest loans or low credit scores, and women being undervalued by 21% in online marketing. Recently, different techniques

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-06-27
Tanner Fiez; Nihar B. Shah; Lillian Ratliff

A number of applications involve sequential arrival of users, and require showing each user an ordering of items. A prime example (which forms the focus of this paper) is the bidding process in conference peer review where reviewers enter the system sequentially, each reviewer needs to be shown the list of submitted papers, and the reviewer then "bids" to review some papers. The order of the papers

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Jordi Ganzer; Natalia Criado; Maite Lopez-Sanchez; Simon Parsons; Juan A. Rodriguez-Aguilar

Inspired by e-participation systems, in this paper we propose a new model to represent human debates and methods to obtain collective conclusions from them. This model overcomes drawbacks of existing approaches by allowing users to introduce new pieces of information into the discussion, to relate them to existing pieces, and also to express their opinion on the pieces proposed by other users. In addition

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-10
Simon Hecker; Dengxin Dai; Alexander Liniger; Luc Van Gool

This paper investigates how end-to-end driving models can be improved to drive more accurately and human-like. To tackle the first issue we exploit semantic and visual maps from HERE Technologies and augment the existing Drive360 dataset with such. The maps are used in an attention mechanism that promotes segmentation confidence masks, thus focusing the network on semantic classes in the image that

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Amy Zhang; Shagun Sodhani; Khimya Khetarpal; Joelle Pineau

Multi-task reinforcement learning is a rich paradigm where information from previously seen environments can be leveraged for better performance and improved sample-efficiency in new environments. In this work, we leverage ideas of common structure underlying a family of Markov decision processes (MDPs) to improve performance in the few-shot regime. We use assumptions of structure from Hidden-Parameter

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-11
Hung-yi Lee; Cheng-Hao Ho; Chien-Fu Lin; Chiung-Chih Chang; Chih-Wei Lee; Yau-Shian Wang; Tsung-Yuan Hsu; Kuan-Yu Chen

Conventional seq2seq chatbot models attempt only to find sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences. In this paper, we investigate four models to scale or adjust the sentiment of the chatbot response: a persona-based model, reinforcement learning, a plug and play model, and CycleGAN, all based on the seq2seq

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Suraj Nair; Silvio Savarese; Chelsea Finn

Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model (future state reconstruction), and that of the downstream planner

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Kundan Krishna; Amy Pavel; Benjamin Schloss; Jeffrey P. Bigham; Zachary C. Lipton

Despite diverse efforts to mine various modalities of medical data, the conversations between physicians and patients at the time of care remain an untapped source of insights. In this paper, we leverage this data to extract structured information that might assist physicians with post-visit documentation in electronic health records, potentially lightening the clerical burden. In this exploratory

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Jorge A. Mendez; Boyu Wang; Eric Eaton

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong learning setting, in which an agent is faced with multiple consecutive tasks over its lifetime, reusing information from previously seen tasks can substantially accelerate

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Aswin Raghavan; Jesse Hostetler; Indranil Sur; Abrar Rahman; Ajay Divakaran

We introduce the eigentask framework for lifelong learning. An eigentask is a pairing of a skill that solves a set of related tasks, paired with a generative model that can sample from the skill's input space. The framework extends generative replay approaches, which have mainly been used to avoid catastrophic forgetting, to also address other lifelong learning goals such as forward knowledge transfer

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Swaroop Mishra; Anjana Arunkumar; Chris Bryan; Chitta Baral

Models that surpass human performance on several popular benchmarks display significant degradation in performance on exposure to Out of Distribution (OOD) data. Recent research has shown that models overfit to spurious biases and hack' datasets, in lieu of learning generalizable features like humans. In order to stop the inflation in model performance -- and thus overestimation in AI systems' capabilities

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Karthik Abinav Sankararaman; Anand Louis; Navin Goyal

In this work, we consider the problem of robust parameter estimation from observational data in the context of linear structural equation models (LSEMs). LSEMs are a popular and well-studied class of models for inferring causality in the natural and social sciences. One of the main problems related to LSEMs is to recover the model parameters from the observational data. Under various conditions on

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Nagarajan Natarajan; Ajaykrishna Karthikeyan; Prateek Jain; Ivan Radicek; Sriram Rajamani; Sumit Gulwani; Johannes Gehrke

We formalize and study programming by rewards'' (PBR), a new approach for specifying and synthesizing subroutines for optimizing some quantitative metric such as performance, resource utilization, or correctness over a benchmark. A PBR specification consists of (1) input features $x$, and (2) a reward function $r$, modeled as a black-box component (which we can only run), that assigns a reward for

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Yaman Kumar; Mehar Bhatia; Anubha Kabra; Jessy Junyi Li; Di Jin; Rajiv Ratn Shah

A significant progress has been made in deep-learning based Automatic Essay Scoring (AES) systems in the past two decades. The performance commonly measured by the standard performance metrics like Quadratic Weighted Kappa (QWK), and accuracy points to the same. However, testing on common-sense adversarial examples of these AES systems reveal their lack of natural language understanding capability

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-14
Jean-Baptiste Tristan; Joseph Tassarotti; Koundinya Vajjha; Michael L. Wick; Anindya Banerjee

As machine learning is increasingly used in essential systems, it is important to reduce or eliminate the incidence of serious bugs. A growing body of research has developed machine learning algorithms with formal guarantees about performance, robustness, or fairness. Yet, the analysis of these algorithms is often complex, and implementing such systems in practice introduces room for error. Proof assistants

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-13
You Li; Ruizhi Chen; Xiaoji Niu; Yuan Zhuang; Zhouzheng Gao; Xin Hu; Naser El-Sheimy

The inertial navigation system (INS) has been widely used to provide self-contained and continuous motion estimation in intelligent transportation systems. Recently, the emergence of chip-level inertial sensors has expanded the relevant applications from positioning, navigation, and mobile mapping to location-based services, unmanned systems, and transportation big data. Meanwhile, benefit from the

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-13
Prajval Kumar Murali; Kourosh Darvish; Fulvio Mastrogiovanni

The Industry 4.0 paradigm promises shorter development times, increased ergonomy, higher flexibility, and resource efficiency in manufacturing environments. Collaborative robots are an important tangible technology for implementing such a paradigm. A major bottleneck to effectively deploy collaborative robots to manufacturing industries is developing task planning algorithms that enable them to recognize

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-09
Shangtong Zhang; Vivek Veeriah; Shimon Whiteson

We present a Reverse Reinforcement Learning (Reverse RL) approach for representing retrospective knowledge. General Value Functions (GVFs) have enjoyed great success in representing predictive knowledge, i.e., answering questions about possible future outcomes such as "how much fuel will be consumed in expectation if we drive from A to B?". GVFs, however, cannot answer questions like "how much fuel

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-10
Rushang Karia; Siddharth Srivastava

Computing goal-directed behavior (sequential decision-making, or planning) is essential to designing efficient AI systems. Due to the computational complexity of planning, current approaches rely primarily upon hand-coded symbolic domain models and hand-coded heuristic-function generators for efficiency. Learned heuristics for such problems have been of limited utility as they are difficult to apply

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-13
Safwan Hossain; Evi Micha; Nisarg Shah

We propose a multi-agent variant of the classical multi-armed bandit problem, in which there are N agents and K arms, and pulling an arm generates a (possibly different) stochastic reward to each agent. Unlike the classical multi-armed bandit problem, the goal is not to learn the "best arm", as each agent may perceive a different arm as best for her. Instead, we seek to learn a fair distribution over

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-13
Nicolas Chan; Elizabeth Polgreen; Sanjit A. Seshia

The performance of a syntax-guided synthesis algorithm is highly dependent on the provision of a good syntactic template, or grammar. Provision of such a template is often left to the user to do manually, though in the absence of such a grammar, state-of-the-art solvers will provide their own default grammar, which is dependent on the signature of the target program to be sythesized. In this work,

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-13
Gustav Sourek; Filip Zelezny

Lifting is an efficient technique to scale up graphical models generalized to relational domains by exploiting the underlying symmetries. Concurrently, neural models are continuously expanding from grid-like tensor data into structured representations, such as various attributed graphs and relational databases. To address the irregular structure of the data, the models typically extrapolate on the

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-11
Zheda Mai; Hyunwoo Kim; Jihwan Jeong; Scott Sanner

Continual learning is a branch of deep learning that seeks to strike a balance between learning stability and plasticity. The CVPR 2020 CLVision Continual Learning for Computer Vision challenge is dedicated to evaluating and advancing the current state-of-the-art continual learning methods using the CORe50 dataset with three different continual learning scenarios. This paper presents our approach,

更新日期：2020-07-15
• arXiv.cs.AI Pub Date : 2020-07-13
Pasquale Minervini; Sebastian Riedel; Pontus Stenetorp; Edward Grefenstette; Tim Rocktäschel

Attempts to render deep learning models interpretable, data-efficient, and robust have seen some success through hybridisation with rule-based systems, for example, in Neural Theorem Provers (NTPs). These neuro-symbolic models can induce interpretable rules and learn representations from data via back-propagation, while providing logical explanations for their predictions. However, they are restricted

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Yana Agafonova; Alexey Tikhonov; Ivan P. Yamshchikov

This papers revisits the receptive theory in context of computational creativity. It presents a case study of a Paranoid Transformer - a fully autonomous text generation engine with raw output that could be read as the narrative of a mad digital persona without any additional human post-filtering. We describe technical details of the generative system, provide examples of output and discuss the impact

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Gustav Sourek; Filip Zelezny; Ondrej Kuzelka

We demonstrate a declarative differentiable programming framework based on the language of Lifted Relational Neural Networks, where small parameterized logic programs are used to encode relational learning scenarios. When presented with relational data, such as various forms of graphs, the program interpreter dynamically unfolds differentiable computational graphs to be used for the program parameter

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Martin C. Cooper

Domain reduction is an essential tool for solving the constraint satisfaction problem (CSP). In the binary CSP, neighbourhood substitution consists in eliminating a value if there exists another value which can be substituted for it in each constraint. We show that the notion of neighbourhood substitution can be strengthened in two distinct ways without increasing time complexity. We also show the

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Ralph Abboud; İsmail İlkan Ceylan; Thomas Lukasiewicz; Tommaso Salvatori

Knowledge base completion (KBC) aims to automatically infer missing facts by exploiting information already present in a knowledge base (KB). A promising approach for KBC is to embed knowledge into latent spaces and make predictions from learned embeddings. However, existing embedding models are subject to at least one of the following limitations: (1) theoretical inexpressivity, (2) lack of support

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Johannes Reich

The aim of this article is to delineate a theory of interaction semantics and thereby provide a proper understanding of the "meaning" of the exchanged characters within an interaction. The idea is to describe the interaction (between discrete systems) by a mechanism that depends on information exchange, that is, on the identical naming of the "exchanged" characters -- by a protocol. Complementing a

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Youngsuk Park; Ryan A. Rossi; Zheng Wen; Gang Wu; Handong Zhao

Linear quadratic regulator (LQR) is one of the most popular frameworks to tackle continuous Markov decision process tasks. With its fundamental theory and tractable optimal policy, LQR has been revisited and analyzed in recent years, in terms of reinforcement learning scenarios such as the model-free or model-based setting. In this paper, we introduce the \textit{Structured Policy Iteration} (S-PI)

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-12
Matthew Guzdial; Devi Acharya; Max Kreminski; Michael Cook; Mirjam Eladhari; Antonios Liapis; Anne Sullivan

Tabletop roleplaying games (TTRPGs) and procedural content generators can both be understood as systems of rules for producing content. In this paper, we argue that TTRPG design can usefully be viewed as procedural content generator design. We present several case studies linking key concepts from PCG research -- including possibility spaces, expressive range analysis, and generative pipelines -- to

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-12
Liwen Li; Zequn Wei; Jin-Kao Hao; Kun He

Knapsack problems are classic models that can formulate a wide range of applications. In this work, we deal with the Budgeted Maximum Coverage Problem (BMCP), which is a generalized 0-1 knapsack problem. Given a set of items with nonnegative weights and a set of elements with nonnegative profits, where each item is composed of a subset of elements, BMCP aims to pack a subset of items in a capacity-constrained

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-12
Faruk Kucuksubasi; Elif Surer

Reinforcement learning (RL) agents are often designed specifically for a particular problem and they generally have uninterpretable working processes. Statistical methods-based agent algorithms can be improved in terms of generalizability and interpretability using symbolic Artificial Intelligence (AI) tools such as logic programming. In this study, we present a model-free RL architecture that is supported

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-11
Dong Xu; Xiao Huang; Joseph Mango; Xiang Li; Zhenlong Li

Conventional simulations on multi-exit indoor evacuation focus primarily on how to determine a reasonable exit based on numerous factors in a changing environment. Results commonly include some congested and other under-utilized exits, especially with massive pedestrians. We propose a multi-exit evacuation simulation based on Deep Reinforcement Learning (DRL), referred to as the MultiExit-DRL, which

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-11
Romit S Beed; Sunita Sarkar; Arindam Roy; Suvranil D Biswas; Suhana Biswas

Carpooling has gained considerable importance in developed as well as in developing countries as an effective solution for controlling vehicular pollution, both sound and air. As carpooling decreases the number of vehicles used by commuters, it results in multiple benefits like mitigation of traffic and congestion on the roads, reduced demand for parking facilities, lesser energy or fuel consumption

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-11
Matthew C. Fontaine; Ruilin Liu; Julian Togelius; Amy K. Hoover; Stefanos Nikolaidis

Recent developments in machine learning techniques have allowed automatic generation of video game levels that are stylistically similar to human-designed examples. While the output of machine learning models such as generative adversarial networks (GANs) is notoriously hard to control, the recently proposed latent variable evolution (LVE) technique searches the space of GAN parameters to generate

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-10
Ondrej Kuzelka

It is known due to the work of Van den Broeck et al [KR, 2014] that weighted first-order model counting (WFOMC) in the two-variable fragment of first-order logic can be solved in time polynomial in the number of domain elements. In this paper we extend this result to the two-variable fragment with counting quantifiers.

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Laura Rieger; Lars Kai Hansen

With machine learning models being used for more sensitive applications, we rely on interpretability methods to prove that no discriminating attributes were used for classification. A potential concern is the so-called "fair-washing" - manipulating a model such that the features used in reality are hidden and more innocuous features are shown to be important instead. In our work we present an effective

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Jer Shyuan Ng; Wei Yang Bryan Lim; Hong-Ning Dai; Zehui Xiong; Jianqiang Huang; Dusit Niyato; Xian-Sheng Hua; Cyril Leung; Chunyan Miao

Due to the advanced capabilities of the Internet of Vehicles (IoV) components such as vehicles, Roadside Units (RSUs) and smart devices as well as the increasing amount of data generated, Federated Learning (FL) becomes a promising tool given that it enables privacy-preserving machine learning that can be implemented in the IoV. However, the performance of the FL suffers from the failure of communication

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Arian Garshi; Malin Wist Jakobsen; Jørgen Nyborg-Christensen; Daniel Ostnes; Maria Ovchinnikova

Artificial intelligence (AI) algorithms have emerged in the educational domain as a tool to make learning more efficient. Different applications for mastering particular skills, learning new languages, and tracking their progress are used by children. What is the impact on children from using this smart technology? We conducted a systematic review to understand the state of the art. We explored the

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Djallel Bouneffouf; Sohini Upadhyay; Yasaman Khazaeni

We consider a novel variant of the contextual bandit problem (i.e., the multi-armed bandit with side-information, or context, available to a decision-maker) where the reward associated with each context-based decision may not always be observed("missing rewards"). This new problem is motivated by certain online settings including clinical trial and ad recommendation applications. In order to address

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Piyush Yadav; Dhaval Salwala; Edward Curry

Complex Event Processing (CEP) is an event processing paradigm to perform real-time analytics over streaming data and match high-level event patterns. Presently, CEP is limited to process structured data stream. Video streams are complicated due to their unstructured data model and limit CEP systems to perform matching over them. This work introduces a graph-based structure for continuous evolving

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-13
Siwei Chen; Xiao Ma; David Hsu

It has been arduous to assess the progress of a policy learning algorithm in the domain of hierarchical task with high dimensional action space due to the lack of a commonly accepted benchmark. In this work, we propose a new light-weight benchmark task called Diner Dash for evaluating the performance in a complicated task with high dimensional action space. In contrast to the traditional Atari games

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-12
Randy Tan; Naimul Khan; Ling Guan

In current deep network architectures, deeper layers in networks tend to contain hundreds of independent neurons which makes it hard for humans to understand how they interact with each other. By organizing the neurons by correlation, humans can observe how clusters of neighbouring neurons interact with each other. In this paper, we propose a novel algorithm for back propagation, called Locality Guided

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-12
Martin Ferianc; Hongxiang Fan; Miguel Rodrigues

In recent years, neural architecture search (NAS) has received intensive scientific and industrial interest due to its capability of finding a neural architecture with high accuracy for various artificial intelligence tasks such as image classification or object detection. In particular, gradient-based NAS approaches have become one of the more popular approaches thanks to their computational efficiency

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-12
Kartik Chugh; Andrea Y. Solis; Thomas D. LaToza

Developers authoring HTML documents define elements following patterns which establish and reflect the visual structure of a document, such as making all images in a footer the same height by applying a class to each. To surface these patterns to developers and support developers in authoring consistent with these patterns, we propose a mixed human-AI technique for creating code patterns. Patterns

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-12
Evan Zheran Liu; Ramtin Keramati; Sudarshan Seshadri; Kelvin Guu; Panupong Pasupat; Emma Brunskill; Percy Liang

Model-based reinforcement learning (RL) is appealing because (i) it enables planning and thus more strategic exploration, and (ii) by decoupling dynamics from rewards, it enables fast transfer to new reward functions. However, learning an accurate Markov Decision Process (MDP) over high-dimensional states (e.g., raw pixels) is extremely challenging because it requires function approximation, which

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-12
Yi Tay; Zhe Zhao; Dara Bahri; Donald Metzler; Da-Cheng Juan

Achieving state-of-the-art performance on natural language understanding tasks typically relies on fine-tuning a fresh model for every task. Consequently, this approach leads to a higher overall parameter cost, along with higher technical maintenance for serving multiple models. Learning a single multi-task model that is able to do well for all the tasks has been a challenging and yet attractive proposition

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-12
Marko Smilevski

Multi-modal Record Linkage is the process of matching multi-modal records from multiple sources that represent the same entity. This field has not been explored in research and we propose two solutions based on Deep Learning architectures that are inspired by recent work in Visual Question Answering. The neural networks we propose use two different fusion modules, the Recurrent Neural Network + Convolutional

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-11
Bapireddy Karri; Sudip Misra; Senior Member IEEE

There is an increased interest in the use of Unmanned Aerial Vehicles (UAVs) for agriculture, military, disaster management and aerial photography around the world. UAVs are scalable, flexible and are useful in various environments where direct human intervention is difficult. In general, the use of UAVs with cameras mounted to them has increased in number due to their wide range of applications in

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-11
Alexander Tschantz; Beren Millidge; Anil K. Seth; Christopher L. Buckley

The field of reinforcement learning can be split into model-based and model-free methods. Here, we unify these approaches by casting model-free policy optimisation as amortised variational inference, and model-based planning as iterative variational inference, within a control as hybrid inference' (CHI) framework. We present an implementation of CHI which naturally mediates the balance between iterative

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-11
Sascha Rosbach; Xing Li; Simon Großjohann; Silviu Homoceanu; Stefan Roth

General-purpose trajectory planning algorithms for automated driving utilize complex reward functions to perform a combined optimization of strategic, behavioral, and kinematic features. The specification and tuning of a single reward function is a tedious task and does not generalize over a large set of traffic situations. Deep learning approaches based on path integral inverse reinforcement learning

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-11
Alvaro H. C. Correia; Robert Peharz; Cassio de Campos

Decision Trees and Random Forests are among the most widely used machine learning models, and often achieve state-of-the-art performance in tabular, domain-agnostic datasets. Nonetheless, being primarily discriminative models they lack principled methods to manipulate the uncertainty of predictions. In this paper, we exploit Generative Forests (GeFs), a recent class of deep probabilistic models that

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-11
Ugurkan Ates

In this paper, we study a long-term planning scenario that is based on drone racing competitions held in real life. We conducted this experiment on a framework created for "Game of Drones: Drone Racing Competition" at NeurIPS 2019. The racing environment was created using Microsoft's AirSim Drone Racing Lab. A reinforcement learning agent, a simulated quadrotor in our case, has trained with the Policy

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-11
Xuejiao Liu; Xueshuang Xiang

Generative adversarial networks (GANs) have been widely used and have achieved competitive results in semi-supervised learning. This paper theoretically analyzes how GAN-based semi-supervised learning (GAN-SSL) works. We first prove that, given a fixed generator, optimizing the discriminator of GAN-SSL is equivalent to optimizing that of supervised learning. Thus, the optimal discriminator in GAN-SSL

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-11
Zhiwei Deng; Karthik Narasimhan; Olga Russakovsky

The ability to perform effective planning is crucial for building an instruction-following agent. When navigating through a new environment, an agent is challenged with (1) connecting the natural language instructions with its progressively growing knowledge of the world; and (2) performing long-range planning and decision making in the form of effective exploration and error correction. Current methods

更新日期：2020-07-14
• arXiv.cs.AI Pub Date : 2020-07-11
Jinfeng Li; Yuliang Li; Xiaolan Wang; Wang-Chiew Tan

Semantic tagging, which has extensive applications in text mining, predicts whether a given piece of text conveys the meaning of a given semantic tag. The problem of semantic tagging is largely solved with supervised learning and today, deep learning models are widely perceived to be better for semantic tagging. However, there is no comprehensive study supporting the popular belief. Practitioners often

更新日期：2020-07-14
Contents have been reproduced by permission of the publishers.

down
wechat
bug