Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 9 of 9
Full-Text Articles in Engineering
Cooperative Deep Q -Learning Framework For Environments Providing Image Feedback, Krishnan Raghavan, Vignesh Narayanan, Sarangapani Jagannathan
Cooperative Deep Q -Learning Framework For Environments Providing Image Feedback, Krishnan Raghavan, Vignesh Narayanan, Sarangapani Jagannathan
Publications
In this article, we address two key challenges in deep reinforcement learning (DRL) setting, sample inefficiency, and slow learning, with a dual-neural network (NN)-driven learning approach. In the proposed approach, we use two deep NNs with independent initialization to robustly approximate the action-value function in the presence of image inputs. In particular, we develop a temporal difference (TD) error-driven learning (EDL) approach, where we introduce a set of linear transformations of the TD error to directly update the parameters of each layer in the deep NN. We demonstrate theoretically that the cost minimized by the EDL regime is an approximation …
Humans And The Core Partition: An Agent-Based Modeling Experiment, Andrew J. Collins, Sheida Etemadidavan
Humans And The Core Partition: An Agent-Based Modeling Experiment, Andrew J. Collins, Sheida Etemadidavan
Engineering Management & Systems Engineering Faculty Publications
Although strategic coalition formation is traditionally modeled using cooperative game theory, behavioral game theorists have repeatedly shown that outcomes predicted by game theory are different from those generated by actual human behavior. To further explore these differences, in a cooperative game theory context, we experiment to compare the outcomes resulting from human participants’ behavior to those generated by a cooperative game theory solution mechanism called the core partition. Our experiment uses an interactive simulation of a glove game, a particular type of cooperative game, to collect the participant’s decision choices and their resultant outcomes. Two different glove games are considered, …
Universal Biological Motions For Educational Robot Theatre And Games, Rajesh Venkatachalapathy, Martin Zwick, Adam Slowik, Kai Brooks, Mikhail Mayers, Roman Minko, Tyler Hull, Bliss Brass, Marek Perkowski
Universal Biological Motions For Educational Robot Theatre And Games, Rajesh Venkatachalapathy, Martin Zwick, Adam Slowik, Kai Brooks, Mikhail Mayers, Roman Minko, Tyler Hull, Bliss Brass, Marek Perkowski
Systems Science Faculty Publications and Presentations
Paper presents a concept that is new to robotics education and social robotics. It is based on theatrical games, in motions for social robots and animatronic robots. Presented here motion model is based on Drift Differential Model from biology and Fokker-Planck equations. This model is used in various areas of science to describe many types of motion. The model was successfully verified on various simulated mobile robots and a motion game of three robots called "Mouse and Cheese."
Proceedings Of The Cuny Games Conference 6.0, Robert O. Duncan, Joseph Bisz, Christina Boyle, Kathleen Offenholley, Maura A. Smale, Carolyn Stallard, Deborah Sturm
Proceedings Of The Cuny Games Conference 6.0, Robert O. Duncan, Joseph Bisz, Christina Boyle, Kathleen Offenholley, Maura A. Smale, Carolyn Stallard, Deborah Sturm
Publications and Research
The CUNY Games Network is an organization dedicated to encouraging research, scholarship and teaching in the developing field of games-based learning. We connect educators from every campus and discipline at CUNY and beyond who are interested in digital and non-digital games, simulations, and other forms of interactive teaching and inquiry-based learning. These proceedings summarize the CUNY Games Conference 6.0, where scholars shared research findings at a three-day event to promote and discuss game-based pedagogy in higher education. Presenters could share findings in oral presentations, posters, demos, or play testing sessions. The conference also included workshops on how to modify existing …
Proceedings Of The Cuny Games Conference 5.0, Robert O. Duncan, Joe Bisz, Julie Cassidy, Kathleen Offenholley, Carolyn Stallard, Deborah Sturm, Anders A. Wallace
Proceedings Of The Cuny Games Conference 5.0, Robert O. Duncan, Joe Bisz, Julie Cassidy, Kathleen Offenholley, Carolyn Stallard, Deborah Sturm, Anders A. Wallace
Publications and Research
The CUNY Games Network is an organization dedicated to encouraging research, scholarship and teaching in the developing field of games-based learning. We connect educators from every campus and discipline at CUNY and beyond who are interested in digital and non-digital games, simulations, and other forms of interactive teaching and inquiry-based learning. The CUNY Games Conference distills its best cutting-edge interactive presentations into a two-day event to promote and discuss game-based pedagogies in higher education, focusing particularly on non-digital learning activities that faculty can use in the classroom every day. The conference will include workshops lead by CUNY Games Organizers on …
Quantitative Jeopardy Feud, Jonathan M. Gallimore
Quantitative Jeopardy Feud, Jonathan M. Gallimore
MSF 600 PR - Gallimore - Fall 2018
This activity - Quantitative Jeopardy Feud - is a method for using a game as a final exam.
Forensic Analysis Of Immersive Virtual Reality Social Applications: A Primary Account, Ananya Yarramreddy, Peter Gromkowski, Ibrahim Baggili
Forensic Analysis Of Immersive Virtual Reality Social Applications: A Primary Account, Ananya Yarramreddy, Peter Gromkowski, Ibrahim Baggili
Electrical & Computer Engineering and Computer Science Faculty Publications
Our work presents the primary account for exploring the forensics of immersive Virtual Reality (VR) systems and their social applications. The Social VR applications studied in this work include Bigscreen, Altspace VR, Rec Room and Facebook Spaces. We explored the two most widely adopted consumer VR systems: the HTC Vive and the Oculus Rift. Our tests examined the efficacy of reconstructing evidence from network traffic as well as the systems themselves. The results showed that a significant amount of forensically relevant data such as user names, user profile pictures, events, and system details may be recovered. We anticipate that this …
Preliminary Forensic Analysis Of The Xbox One, Jason Moore, Ibrahim Baggili, Andrew Marrington, Armindo Rodrigues
Preliminary Forensic Analysis Of The Xbox One, Jason Moore, Ibrahim Baggili, Andrew Marrington, Armindo Rodrigues
Electrical & Computer Engineering and Computer Science Faculty Publications
Video game consoles can no longer be viewed as just gaming consoles but rather as full multimedia machines, capable of desktop computer-like performance. The past has shown that game consoles have been used in criminal activities such as extortion, identity theft, and child pornography, but with their ever-increasing capabilities, the likelihood of the expansion of criminal activities conducted on or over the consoles increases. This research aimed to take the initial step of understanding the Xbox One, the most powerful Microsoft console to date. We report the outcome of conducting a forensic examination of the Xbox One, and we provide …
One Fish, Two Fish, Red Fish, Blue Fish: The Use Of Simple Agent-Based Models And Role-Play Games To Communicate Key Messages To Community Groups, Deborah Cleland, Rollan Geronimo, A Dray, Pascal Perez, Abigail Trinidad
One Fish, Two Fish, Red Fish, Blue Fish: The Use Of Simple Agent-Based Models And Role-Play Games To Communicate Key Messages To Community Groups, Deborah Cleland, Rollan Geronimo, A Dray, Pascal Perez, Abigail Trinidad
Professor Pascal Perez
The principal anthropogenic factors driving reef degradation have been known for years, if not decades. Overfishing, sedimentation and nutrient loads are just some of the key impacts of human activities in and around reef communities. Therefore, the future of reefs does not rely on generating new knowledge, but rather on implementing and integrating the knowledge we already have. This will require creating effective links between researchers, managers and communities to promote mutual learning, negotiation and collaborative action for reef management. Combining agent-based models and role-play games, through a technique known as Companion Modelling (ComMod), creates a dynamic and interactive setting …