csAI – Newsemia

Alternative Function Approximation Parameterizations for Solving Games: An Analysis of $f$-Regression Counterfactual Regret Minimization. (arXiv:1912.02967v1 [cs.AI])

NewsemiaDecember 9, 2019

by NewsemiaDecember 9, 201900

Function approximation is a powerful approach for structuring large decision problems that has facilitated great achievements in the areas of reinforcement learning and game playing....

AI/ML

Reinforcement Learning Upside Down: Don't Predict Rewards — Just Map Them to Actions. (arXiv:1912.02875v1 [cs.AI])

NewsemiaDecember 9, 2019

by NewsemiaDecember 9, 201900

We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL)....

AI/ML

Inter-Level Cooperation in Hierarchical Reinforcement Learning. (arXiv:1912.02368v1 [cs.AI])

NewsemiaDecember 8, 2019

by NewsemiaDecember 8, 201900

This article presents a novel algorithm for promoting cooperation between internal actors in a goal-conditioned hierarchical reinforcement learning (HRL) policy. Current techniques for HRL policy...

AI/ML

Improving Policies via Search in Cooperative Partially Observable Games. (arXiv:1912.02318v1 [cs.AI])

NewsemiaDecember 7, 2019

by NewsemiaDecember 7, 201900

Recent superhuman results in games have largely been achieved in a variety of zero-sum settings, such as Go and Poker, in which agents need to...

AI/ML

Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning. (arXiv:1912.02288v1 [cs.AI])

NewsemiaDecember 7, 2019

by NewsemiaDecember 7, 201900

In recent years we have seen fast progress on a number of benchmark problems in AI, with modern methods achieving near or super human performance...

AI/ML

Towards Successful Collaboration: Design Guidelines for AI-based Services enriching Information Systems in Organisations. (arXiv:1912.01077v1 [cs.AI])

NewsemiaDecember 4, 2019

by NewsemiaDecember 4, 201900

Information systems (IS) are widely used in organisations to improve business performance. The steady progression in improving technologies like artificial intelligence (AI) and the need...

AI/ML

Towards Universal Languages for Tractable Ontology Mediated Query Answering. (arXiv:1911.11359v1 [cs.AI])

NewsemiaNovember 27, 2019

by NewsemiaNovember 27, 201900

An ontology language for ontology mediated query answering (OMQA-language) is universal for a family of OMQA-languages if it is the most expressive one among this...

AI/ML

Verbal Programming of Robot Behavior. (arXiv:1911.09782v1 [cs.AI])

NewsemiaNovember 25, 2019

by NewsemiaNovember 25, 201900

Home robots may come with many sophisticated built-in abilities, however there will always be a degree of customization needed for each user and environment. Ideally...

AI/ML

TrueLearn: A Family of Bayesian Algorithms to Match Lifelong Learners to Open Educational Resources. (arXiv:1911.09471v1 [cs.AI])

NewsemiaNovember 24, 2019

by NewsemiaNovember 24, 201900

The recent advances in computer-assisted learning systems and the availability of open educational resources today promise a pathway to providing cost-efficient, high-quality education to large...

AI/ML

Generalized Planning with Positive and Negative Examples. (arXiv:1911.09365v1 [cs.AI])

NewsemiaNovember 24, 2019

by NewsemiaNovember 24, 201900

Generalized planning aims at computing an algorithm-like structure (generalized plan) that solves a set of multiple planning instances. In this paper we define negative examples...

AI/ML

Integrating Automated Play in Level Co-Creation. (arXiv:1911.09219v1 [cs.AI])

NewsemiaNovember 23, 2019

by NewsemiaNovember 23, 201900

In level co-creation an AI and human work together to create a video game level. One open challenge in level co-creation is how to empower...

AI/ML

Generating Interactive Worlds with Text. (arXiv:1911.09194v1 [cs.AI])

NewsemiaNovember 23, 2019

by NewsemiaNovember 23, 201900

Procedurally generating cohesive and interesting game environments is challenging and time-consuming. In order for the relationships between the game elements to be natural, common-sense has...

AI/ML

Adversarial Inverse Reinforcement Learning for Decision Making in Autonomous Driving. (arXiv:1911.08044v1 [cs.AI])

NewsemiaNovember 20, 2019

by NewsemiaNovember 20, 201900

Generative Adversarial Imitation Learning (GAIL) is an efficient way to learn sequential control strategies from demonstration. Adversarial Inverse Reinforcement Learning (AIRL) is similar to GAIL...

AI/ML

The {alpha}{mu} Search Algorithm for the Game of Bridge. (arXiv:1911.07960v1 [cs.AI])

NewsemiaNovember 20, 2019

by NewsemiaNovember 20, 201900

{alpha}{mu} is an anytime heuristic search algorithm for incomplete information games that assumes perfect information for the opponents. {alpha}{mu} addresses the strategy fusion and non-locality...

AI/ML

Fine-grained Qualitative Spatial Reasoning about Point Positions. (arXiv:1911.06543v1 [cs.AI])

NewsemiaNovember 18, 2019

by NewsemiaNovember 18, 201900

The ability to persist in the spacial environment is, not only in the robotic context, an essential feature. Positional knowledge is one of the most...

AI/ML

"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations. (arXiv:1911.06473v1 [cs.AI])

NewsemiaNovember 18, 2019

by NewsemiaNovember 18, 201900

As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on...

AI/ML

Generating Persona Consistent Dialogues by Exploiting Natural Language Inference. (arXiv:1911.05889v1 [cs.AI])

NewsemiaNovember 18, 2019

by NewsemiaNovember 18, 201900

Consistency is one of the major challenges faced by dialogue agents. A human-like dialogue agent should not only respond naturally, but also maintain a consistent...

AI/ML

Deception through Half-Truths. (arXiv:1911.05885v1 [cs.AI])

NewsemiaNovember 17, 2019

by NewsemiaNovember 17, 201900

Deception is a fundamental issue across a diverse array of settings, from cybersecurity, where decoys (e.g., honeypots) are an important tool, to politics that can...

AI/ML

Partial-Order, Partially-Seen Observations of Fluents or Actions for Plan Recognition as Planning. (arXiv:1911.05876v1 [cs.AI])

NewsemiaNovember 17, 2019

by NewsemiaNovember 17, 201900

This work aims to make plan recognition as planning more ready for real-world scenarios by adapting previous compilations to work with partial-order, half-seen observations of...

AI/ML

SHACL Constraints with Inference Rules. (arXiv:1911.00598v1 [cs.AI])

NewsemiaNovember 5, 2019

by NewsemiaNovember 5, 201900

The Shapes Constraint Language (SHACL) has been recently introduced as a W3C recommendation to define constraints that can be validated against RDF graphs. Interactions of...