Spontaneous Theory of Mind for Artificial Intelligence

no code implementations • 16 Feb 2024 • Nikolos Gurney, David V. Pynadath, Volkan Ustun

Existing approaches to Theory of Mind (ToM) in Artificial Intelligence (AI) overemphasize prompted, or cue-based, ToM, which may limit our collective ability to develop Artificial Social Intelligence (ASI).

Controlling Synthetic Characters in Simulations: A Case for Cognitive Architectures and Sigma

no code implementations • 6 Jan 2021 • Volkan Ustun, Paul S. Rosenbloom, Seyed Sajjadi, Jeremy Nuttal

Simulations, along with other similar applications like virtual worlds and video games, require computational models of intelligence that generate realistic and credible behavior for the participating synthetic characters.

Distributional Reinforcement Learning Unity

Adaptive Synthetic Characters for Military Training

no code implementations • 6 Jan 2021 • Volkan Ustun, Rajay Kumar, Adam Reilly, Seyed Sajjadi, Andrew Miller

Observation-based behavior model adaptation that leverages machine learning and the experience of synthetic entities in combination with appropriate prior knowledge can address the issues in the existing computational behavior models to create a better training experience in military training simulations.

BIG-bench Machine Learning Imitation Learning +1

Combining Distributed Vector Representations for Words

no code implementations • WS 2015 • Justin Garten, Kenji Sagae, Volkan Ustun, Morteza Dehghani

Outperforming Word2Vec on Analogy Tasks with Random Projections

no code implementations • 20 Dec 2014 • Abram Demski, Volkan Ustun, Paul Rosenbloom, Cody Kommers

We present a distributed vector representation based on a simplification of the BEAGLE system, designed in the context of the Sigma cognitive architecture.

Dimensionality Reduction