16,778 Hits in 4.3 sec

Classification of Online Game Players Using Action Transition Probability and Kullback Leibler Entropy

Ruck Thawonmas, Ji-Young Ho
2007 Journal of Advanced Computational Intelligence and Intelligent Informatics  
Online game players are more satisfied with contents tailored to their preferences. Player classification is necessary for determining which classes players belong to.  ...  In experiments with two online game simulators, Zereal and Simac, our approach performed better than an existing approach based on action frequency and comparably to another existing approach using the  ...  We thank the reviewers for their invaluable comments.  ... 
doi:10.20965/jaciii.2007.p0319 fatcat:mrhdhbqb55gm7l76qmaaqhsjvy

High-Fidelity Simulated Players for Interactive Narrative Planning

Pengcheng Wang, Jonathan Rowe, Wookhee Min, Bradford Mott, James Lester
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
A promising approach to addressing this challenge is creating simulated players whose behaviors closely approximate those of human players.  ...  In this paper, we propose a novel approach to generating high-fidelity simulated players based on deep recurrent highway networks and deep convolutional networks.  ...  Zook et al. [2015] used automated planning agents to simulate humans to generate game playthroughs.  ... 
doi:10.24963/ijcai.2018/540 dblp:conf/ijcai/WangRMML18 fatcat:6jddqljynfgb3mve2bifxx5qju

Data-driven dynamic decision models

John J. Nay, Jonathan M. Gilligan
2015 2015 Winter Simulation Conference (WSC)  
This is useful for designing empirically grounded agent-based simulations and for gaining direct insight into observed dynamic processes.  ...  We also demonstrate the method's ability to recover known data-generating processes by simulating data with agent-based models and correctly deriving the underlying decision models for multiple agent models  ...  We would like to thank Yevgeniy Vorobeychik for discussions on predicting games. This work was supported by U.S. National Science Foundation grants EAR-1416964 and EAR-1204685.  ... 
doi:10.1109/wsc.2015.7408381 dblp:conf/wsc/NayG15 fatcat:vvkfas6yxzgt7eanxv6vn72tsq

A Survey on Coordination Methodologies for Simulated Robotic Soccer Teams

Fernando Almeida, Nuno Lau, Luís Paulo Reis
2010 Multi-Agent Logics, Languages, and Organisations Federated Workshops  
RoboCup provides a pragmatic testbed based on standardized platforms for the systematic evaluation of developed MAS coordination techniques.  ...  This initiative encompasses a simulated robotic soccer league in which 11 against 11 simulated robots play a realistic soccer game that is particularly suited for researching coordination methodologies  ...  The methods proposed to aid players weigh the cost/benefit ratio for deciding to switch positions are based on: • Role Exchange: continuously assesses the usefulness of exchanging positions based on tactical  ... 
dblp:conf/mallow/AlmeidaLR10 fatcat:snj52oys6zholf527iyul5zhma

Design of simulation-based pilot training systems using machine learning agents

J. Källström, R. Granlund, F. Heintz
2022 Aeronautical Journal  
to utilise learning agents for improved training value.  ...  In particular, if constructive simulations, which provide synthetic agents operating synthetic vehicles, were used to a higher degree, complex training scenarios could be realised at low cost, the need  ...  This work was partially supported by the Swedish Governmental Agency for Innovation Systems (grant NFFP7/2017-04885), and the Wallenberg Artificial Intelligence, Autonomous Systems and Software Program  ... 
doi:10.1017/aer.2022.8 fatcat:ywawtvniqjdztca4wb2o7zz5hq

A review of interactive narrative systems and technologies: a training perspective

Linbo Luo, Wentong Cai, Suiping Zhou, Michael Lees, Haiyan Yin
2015 Simulation (San Diego, Calif.)  
Recently, there is an emerging trend to apply interactive narrative for training and simulation.  ...  In simulation-based training, the use of an interactive narrative system enables the possibility to offer engaging, diverse and personalized narratives or scenarios for different training purposes.  ...  Controllability In simulation-based training, a trainer has the role to direct the training towards certain training objectives.  ... 
doi:10.1177/0037549714566722 fatcat:jifpa3w6wzcapbq5yra3k3jgxe

Training for emergency response with RimSim:Response!

Bruce D. Campbell, Konrad A. Schroder, Dawn A. Trevisani
2009 Modeling and Simulation for Military Operations IV  
We present initial findings from interacting with a wide variety of mixed agent simulation sessions and make the software available for others to perform their own experiments.  ...  Agents implement response heuristics and communications strategies in conjunction with live players trying to develop their own heuristics and communications strategies to participate in a successful community  ...  funding and support for the RimSim project.  ... 
doi:10.1117/12.819337 fatcat:elrmofgew5cxro3d7if4oqzyqa

Applied Machine Learning for Games: A Graduate School Course [article]

Yilei Zeng, Aayush Shah, Jameson Thai, Michael Zyda
2021 arXiv   pre-print
Student projects cover use-cases such as training AI-bots in gaming benchmark environments and competitions, understanding human decision patterns in gaming, and creating intelligent non-playable characters  ...  or environments to foster engaging gameplay.  ...  Using object detection models based on Single-Shot Detection and Retinanet, an agent was trained to play the game while distinguishing friends from foes.  ... 
arXiv:2012.01148v2 fatcat:f44ln32jnbfhrearv234ylteru

Data-driven sequential goal selection model for multi-agent simulation

Wenxi Liu, Zhe Huang, Rynson W. H. Lau, Dinesh Manocha
2014 Proceedings of the 20th ACM Symposium on Virtual Reality Software and Technology - VRST '14  
In our paper, we present a crowd simulation algorithm that allows a large number of virtual agents to navigate around the virtual world autonomously by sequentially selecting the goals.  ...  Our approach is based on our sequential goal selection model (SGS) which can learn goal-selection patterns from synthetic sequences.  ...  Acknowledgements This research is partially supported by National Science Foundation and a grant from the Boeing Company.  ... 
doi:10.1145/2671015.2671024 dblp:conf/vrst/LiuHLM14 fatcat:smm7rkq37veohnwbkw7shmrphi

The Efficacy of Choosing Strategy with General Regression Neural Network on Evolutionary Markov Games

Shirin Kordnoori, Hamidreza Mostafaei, Mohammadmohsen Ostadrahimi, Saeed Agha Banihashemi
2021 IPTEK: The Journal for Technology and Science  
Boltzmann distribution is used for transition probability and the General Regression Neural Network (GRNN) simulating the strategy-choosing in Evolutionary Markov Games.  ...  Also, the error rate of the GRNN training by Tit for Tat (TFT) strategy is lower than similar work and shows a better result.  ...  If the state transfers from to , then can be the payoff and a series of rewards for state transition, which are stochastic variables.  ... 
doi:10.12962/j20882033.v32i1.7074 fatcat:44ijptxtyfcsjlinz2e7s5eiqi

Reviews of Social Embodiment for Design of Non-Player Characters in Virtual Reality-Based Social Skill Training for Autistic Children

Jewoong Moon
2018 Multimodal Technologies and Interaction  
To build up the training environment for autistic children, it is necessary to identify how to simulate social components in the training.  ...  The purpose of this paper is to review the scholarly works regarding social embodiment aligned with the design of non-player characters in virtual reality (VR)-based social skill training for autistic  ...  This website filters in many academic sources from publishers and scholarly societies. Table 1 . 1 Design factors to simulate a VR-based social skill training.  ... 
doi:10.3390/mti2030053 fatcat:ge6lscmftjdy3cagrl6b2wr56m

Imitation Learning of Team-play in Multiagent System based on Hidden Markov Modeling

Itsuki Noda
2003 International Joint Conference on Artificial Intelligence  
The key of the proposed model is introduction of gate probabilities that restrict transition among agents' intentions according to others' intentions.  ...  This paper addresses agents' intentions as building blocks of imitation learning that abstract local situations of the agent, and proposes a hierarchical hidden Markov model (HMM) to represent cooperative  ...  Two HMM c s for agent X (the first player) and Y (the second player) are constructed after the training of the HMJVTs.  ... 
dblp:conf/ijcai/Noda03 fatcat:ezzx5vpzprdpfjdf7mqr5jgkhm

Development of a distributed multi‐player computer game for scientific experimentation of team training protocols

Sen Cao Richard, Richard A. Volz, Jamison Johnson, Jonathan Whetzel, Dianxiang Xu, Maitreyi Nanjanath
2004 Electronic library  
., which players play which roles), mixed teams of human and intelligent software agents, synchronization of multiple player teams across a network, coordination of a formal experiment encompassing several  ...  We based our development on the game Space Fortress, which has been widely used by cognitive psychologists for studying training protocols.  ...  If an experiment uses intelligent agents to help training, they can be specified to take abstract players, abstract agents, and roles.  ... 
doi:10.1108/02640470410520104 fatcat:elmtqwhdonfwdkxjul3re2srae

A Formalization of the Coach Problem [chapter]

G. Y. R. Schropp, J-J. Ch. Meyer, S. Ramamoorthy
2015 Lecture Notes in Computer Science  
The framework is based on agent organizations [14] , in which social coordination and norms play an important part.  ...  Furthermore, in providing them with appropriate advice, he should still adhere to the norms and regulations of the match to prevent penalties for his team.  ...  Based on these roles, agents have certain (sub-)objectives to achieve and norms to adhere to.  ... 
doi:10.1007/978-3-319-18615-3_28 fatcat:torjrbaqsbg43lrruqdzb32krq

Components of an Incident Management Simulation and Gaming Framework and Related Developments

Sanjay Jain, Charles R. McLean
2008 Simulation (San Diego, Calif.)  
Examples of relevant available models and simulators from the recent literature are identified for each simulation component.  ...  The associated research should prove to be very useful for integrated simulations for incident management, particularly for training applications.  ...  Simulation-based learning applications could be developed for use in stand-alone mode or distributed multiplayer mode to enable team training.  ... 
doi:10.1177/0037549708088956 fatcat:qdndptaopfb37dqpd4wv5itl4u
« Previous Showing results 1 — 15 out of 16,778 results