522,556 Hits in 4.7 sec

AI in Games: Techniques, Challenges and Opportunities [article]

Qiyue Yin, Jun Yang, Wancheng Ni, Bin Liang, Kaiqi Huang
2021 arXiv   pre-print
Through this survey, we 1) compare the main difficulties among different kinds of games for the intelligent decision making field ; 2) illustrate the mainstream frameworks and techniques for developing  ...  With breakthrough of AlphaGo, AI in human-computer game has become a very hot topic attracting researchers all around the world, which usually serves as an effective standard for testing artificial intelligence  ...  Firstly, to train each generation of agents, those AIs utilize different self-play or advanced self-play mechanisms.  ... 
arXiv:2111.07631v1 fatcat:g4sbl6v73rg4jdijj4qfi3eusq

ColosseumRL: A Framework for Multiagent Reinforcement Learning in N-Player Games [article]

Alexander Shmakov, John Lanier, Stephen McAleer, Rohan Achar, Cristina Lopes, Pierre Baldi
2019 arXiv   pre-print
In this paper we present a new framework for research in reinforcement learning in n-player games.  ...  While playing a Nash equilibrium strategy in a two-player zero-sum game is optimal, in an n-player general sum game, it becomes a much less informative solution concept.  ...  To that end, we have created a framework for reinforcement learning in n-player general sum games.  ... 
arXiv:1912.04451v1 fatcat:m5zhpxpwcvax3hg6mmjjmtzefq

Manipulating the Distributions of Experience used for Self-Play Learning in Expert Iteration [article]

Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson, Cameron Browne
2020 arXiv   pre-print
Expert Iteration (ExIt) is an effective framework for learning game-playing policies from self-play.  ...  Thirdly, a trained exploratory policy is used to diversify the trajectories experienced in self-play.  ...  We thank Shayegan Omidshafiei for guidance on the α-rank evaluations.  ... 
arXiv:2006.00283v1 fatcat:egdnda3jovf47jpfjyfguktvse

Correlation-based approach to analysis of spiking networks

Michael Krumin, Shy Shoham
2010 BMC Neuroscience  
We demonstrate that the resulting Linear-Nonlinear-Hawkes (LNH) framework is capable of capturing the dynamics of spike trains with a generally richer multi-correlation structure.  ...  Here, we extend this framework by deriving closed-form expressions for the correlation structure of a more powerful multivariate self-and mutually-exciting Hawkes model class that is driven by exogenous  ...  We demonstrate that the resulting Linear-Nonlinear-Hawkes (LNH) framework is capable of capturing the dynamics of spike trains with a generally richer multi-correlation structure.  ... 
doi:10.1186/1471-2202-11-s1-p182 pmcid:PMC3090890 fatcat:tit3xsmcnbhuhe2vu5xfea2t7q

A Comparison of Self-Play Algorithms Under a Generalized Framework [article]

Daniel Hernandez, Kevin Denamganai, Sam Devlin, Spyridon Samothrakis, James Alfred Walker
2020 arXiv   pre-print
This framework is framed as an approximation to a theoretical solution concept for multiagent training.  ...  We also provide insights on interpreting quantitative metrics of performance for self-play training.  ...  Gupta for his insightful conversations and work on Nash averaging.  ... 
arXiv:2006.04471v1 fatcat:6jpsg2hpknb7jbkrd7pmhrbn5u

Autonomous Industrial Management via Reinforcement Learning: Self-Learning Agents for Decision-Making – A Review [article]

Leonardo A. Espinosa Leal, Magnus Westerlund, Anthony Chapman
2019 arXiv   pre-print
We then introduce self-play scenarios and how they can be used to teach self-learning agents through a supportive environment which focuses on how the agents can adapt to different real-world environments  ...  Once generalization is achieved, we discuss how these can be used to develop self-learning agents.  ...  Fictitious Self-Play is a machine learning framework that implements fictitious play in a sample-based fashion [36] .  ... 
arXiv:1910.08942v1 fatcat:wbpy3iijhbfwxeatiy4ztt5f2m

Hyper-Parameter Sweep on AlphaZero General [article]

Hui Wang, Michael Emmerich, Mike Preuss, Aske Plaat
2019 arXiv   pre-print
Overall, experimental results show that different values can lead to different training results, proving the importance of such a parameter sweep.  ...  For each parameter, we train 3 models using 3 different values (minimum value, default value, maximum value).  ...  During a pure iteration, the first stage is self-play. The player plays several games against to itself to generate games data for further training.  ... 
arXiv:1903.08129v1 fatcat:ostlc34i3nan3eajxj36nveqwa

Do cognitive training strategies improve motor and positive psychological skills development in soccer players? Insights from a systematic review

Maamer Slimani, Nicola Luigi Bragazzi, David Tod, Alexandre Dellal, Olivier Hue, Foued Cheour, Lee Taylor, Karim Chamari
2016 Journal of Sports Sciences  
Regarding imagery, the combination of two different types of cognitive imagery training (i.e., cognitive general and cognitive specific) have a positive influence on soccer performance during training,  ...  age, standard and playing position of the players.  ...  Theoretical/conceptual framework Assuming a well-established theoretical perspective is crucial for conducting a scientifically sound psychological investigation, both for designing an intervention and  ... 
doi:10.1080/02640414.2016.1254809 pmid:27842463 fatcat:cm7qbg6sgvfsxb2zplexhj6kx4

Leaping through Hurdles: Adaptability among Female Athletes

Arvin A. Andacao, Carla Jane B. Linganay
2021 International Journal of Human Movement and Sports Sciences  
Moreover, the authors recommend the RID Adaptation Framework as a guide for the athletes to play and future researchers for further investigation and improvement of this context.  ...  Basketball is a popular team sport played mostly by men. However, female athletes are quite daunting to play.  ...  Sumile for approval of the study. Our indebted gratitude to Dr. Maria Gloria R. Lugo, Mr. Jumher Dave J. Pajarillaga, and Ms. Niña Alyssa M. Santiago for the nitty-gritty of this paper.  ... 
doi:10.13189/saj.2021.091308 fatcat:sjn6dyoyrrg6pnqm4g2vdf3auq

Generating Automatic Curricula via Self-Supervised Active Domain Randomization [article]

Sharath Chandra Raparthy, Bhairav Mehta, Florian Golemo, Liam Paull
2020 arXiv   pre-print
As a result, we extend the self-play framework to jointly learn a goal and environment curriculum, leading to an approach that learns the most fruitful domain randomization strategy with self-play.  ...  Recent work on robotic agents has shown that varying the environment during training, for example with domain randomization, leads to more robust transfer.  ...  Advanced Research (CI-FAR) and Nvidia for donating a DGX-1 for computation.  ... 
arXiv:2002.07911v2 fatcat:7csdcamosjejdbajospd2z6xbm

Rapid prototyping framework for robot-assisted training of autistic children

Min-Gyu Kim, Emilia Barakova, Tino Lourens
2014 The 23rd IEEE International Symposium on Robot and Human Interactive Communication  
This paper describes a rapid prototyping framework for robot-assisted training of children with Autism Spectrum Disorder (ASD).  ...  The main goal of this research is to provide a framework which translates the knowledge from the evidenced Pivotal Response Training to end-user tools, that allow therapists to program/adapt a training  ...  ACKNOWLEDGMENT We would like to acknowledge ZonMW, The Netherlands Organization for Health Research and Development (project number 95103010, ZonMW Programma Translationeel Onderzoek).  ... 
doi:10.1109/roman.2014.6926278 dblp:conf/ro-man/KimBL14 fatcat:oswm3acn3jcm5hichdddchrgiu

Building a Conversational Agent Overnight with Dialogue Self-Play [article]

Pararth Shah, Dilek Hakkani-Tür, Gokhan Tür, Abhinav Rastogi, Ankur Bapna, Neha Nayak, Larry Heck
2018 arXiv   pre-print
We propose Machines Talking To Machines (M2M), a framework combining automation and crowdsourcing to rapidly bootstrap end-to-end dialogue agents for goal-oriented dialogues in arbitrary domains.  ...  In the first phase, a simulated user bot and a domain-agnostic system bot converse to exhaustively generate dialogue "outlines", i.e. sequences of template utterances and their semantic parses.  ...  Acknowledgements We thank Georgi Nikolov, Amir Fayazi, Anna Khasin and Grady Simon for valuable support in design, implementation and evaluation of M2M. References  ... 
arXiv:1801.04871v1 fatcat:l7drdfikljhuzdbsixv5r5o6zi

Short Video-based Advertisements Evaluation System: Self-Organizing Learning Approach [article]

Yunjie Zhang, Fei Tao, Xudong Liu, Runze Su, Xiaorong Mei, Weicong Ding, Zhichen Zhao, Lei Yuan, Ji Liu
2020 arXiv   pre-print
In this paper, we proposed a novel end-to-end self-organizing framework for user behavior prediction.  ...  With the rising of short video apps, such as TikTok, Snapchat and Kwai, advertisement in short-term user-generated videos (UGVs) has become a trending form of advertising.  ...  To tackle the shortages mentioned above, we develop a self-organizing framework, which is able to explore the optimal topology of neural network architecture through training data.  ... 
arXiv:2010.12662v1 fatcat:3vknt7yvfvaybby2namglt6ffy

PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation [article]

Yihua Cheng, Yiwei Bao, Feng Lu
2021 arXiv   pre-print
We design a plug-and-play self-adversarial framework for the gaze feature purification.  ...  Different from common domain adaption methods, we propose a domain generalization method to improve the cross-domain performance without touching target samples.  ...  A.6. Pseudo Code We also provide the pseudo code of the self-adversarial framework (PureGaze) in Fig. 12 .  ... 
arXiv:2103.13173v2 fatcat:i6sw7keyj5cw3cin2znqexjsxq

Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning

Pararth Shah, Dilek Hakkani-Tur, Bing Liu, Gokhan Tur
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)  
In this paper, we study a recently proposed approach for building an agent for arbitrary tasks by combining dialogue self-play and crowd-sourcing to generate fully-annotated dialogues with diverse and  ...  For goal-oriented dialogues, such datasets are expensive to collect and annotate, since each task involves a separate schema and database of entities.  ...  The self-play step also uses a programmed system agent that generates valid system turns for a given task.  ... 
doi:10.18653/v1/n18-3006 dblp:conf/naacl/ShahHLT18 fatcat:hcqveak5ena7rgi25wd73xjrf4
« Previous Showing results 1 — 15 out of 522,556 results