AvE: Assistance via Empowerment. (arXiv:2006.14796v1 [cs.AI])
One difficulty in using artificial agents for human-assistive applications lies in the challenge of accurately assisting with a person’s goal(s). Existing methods tend to rely...
Tag: csAI
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance. (arXiv:2006.14779v1 [cs.AI])
Increasingly, organizations are pairing humans with AI systems to improve decision-making and reducing costs. Proponents of human-centered AI argue that team performance can even further...
A Methodology for Creating Question Answering Corpora Using Inverse Data Annotation. (arXiv:2004.07633v2 [cs.AI] UPDATED)
In this paper, we introduce a novel methodology to efficiently construct a corpus for question answering over structured data. For this, we introduce an intermediate...
Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning. (arXiv:1912.03851v3 [cs.AI] UPDATED)
We use Asynchronous Advantage Actor Critic (A3C) for implementing an AI agent in the controllers that optimize flow of traffic across a single intersection and...
Towards a Metric for Automated Conversational Dialogue System Evaluation and Improvement. (arXiv:1909.12066v2 [cs.AI] UPDATED)
We present “AutoJudge”, an automated evaluation method for conversational dialogue systems. The method works by first generating dialogues based on self-talk, i.e. dialogue systems talking...
Learning Task-General Representations with Generative Neuro-Symbolic Modeling. (arXiv:2006.14448v1 [cs.AI])
A hallmark of human intelligence is the ability to interact directly with raw data and acquire rich, general-purpose conceptual representations. In machine learning, symbolic models...
Plausible Reasoning about EL-Ontologies using Concept Interpolation. (arXiv:2006.14437v1 [cs.AI])
Description logics (DLs) are standard knowledge representation languages for modelling ontologies, i.e. knowledge about concepts and the relations between them. Unfortunately, DL ontologies are difficult...
SOAC: The Soft Option Actor-Critic Architecture. (arXiv:2006.14363v1 [cs.AI])
The option framework has shown great promise by automatically extracting temporally-extended sub-tasks from a long-horizon task. Methods have been proposed for concurrently learning low-level intra-option...
Learn to Earn: Enabling Coordination within a Ride Hailing Fleet. (arXiv:2006.10904v1 [cs.AI])
The problem of optimizing social welfare objectives on multi sided ride hailing platforms such as Uber, Lyft, etc., is challenging, due to misalignment of objectives...
COVID-ABS: An Agent-Based Model of COVID-19 Epidemic to Simulate Health and Economic Effects of Social Distancing Interventions. (arXiv:2006.10532v1 [cs.AI])
The COVID-19 pandemic due to the SARS-CoV-2 coronavirus have directly impacted the public health and economy. To overcome this problem, the countries have adopted different...
Practical Large-Scale Distributed Parallel Monte-Carlo Tree Search Applied to Molecular Design. (arXiv:2006.10504v1 [cs.AI])
It is common practice to use large computational resources to train neural networks, as is known from many examples, such as reinforcement learning applications. However,...
A Study on AI-FML Robotic Agent for Student Learning Behavior Ontology Construction. (arXiv:2006.10228v1 [cs.AI])
In this paper, we propose an AI-FML robotic agent for student learning behavior ontology construction which can be applied in English speaking and listening domain....
Marginal Utility for Planning in Continuous or Large Discrete Action Spaces. (arXiv:2006.06054v1 [cs.AI])
Sample-based planning is a powerful family of algorithms for generating intelligent behavior from a model of the environment. Generating good candidate actions is critical to...
5* Knowledge Graph Embeddings with Projective Transformations. (arXiv:2006.04986v1 [cs.AI])
Performing link prediction using knowledge graph embedding (KGE) models is a popular approach for knowledge graph completion. Such link predictions are performed by measuring the...
A Group-Theoretic Framework for Knowledge Graph Embedding. (arXiv:2005.10956v1 [cs.AI])
We demonstrated the existence of a group algebraic structure hidden in relational knowledge embedding problems, which suggests that a group-based embedding framework is essential for...
Information Acquisition Under Resource Limitations in a Noisy Environment. (arXiv:2005.10383v1 [cs.AI])
We introduce a theoretical model of information acquisition under resource limitations in a noisy environment. An agent must guess the truth value of a given...