Filters








2,702 Hits in 8.1 sec

Building a player strategy model by analyzing replays of real-time strategy games

Ji-Lung Hsieh, Chuen-Tsai Sun
2008 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)  
Developing computer-controlled groups to engage in combat, control the use of limited resources, and create units and buildings in Real-Time Strategy(RTS) Games is a novel application in game AI.  ...  Instead of setting up new programming environments or building a large amount of agent's decision rules by player's experience for conducting real-time AI research, the authors use replays of the commercial  ...  In RTS games, players control their own units and engage in real time combat.  ... 
doi:10.1109/ijcnn.2008.4634237 dblp:conf/ijcnn/HsiehS08 fatcat:gs5na43di5c6lcudps7obhqud4

MOBA-Slice: A Time Slice Based Evaluation Framework of Relative Advantage between Teams in MOBA Games [article]

Lijun Yu, Dawei Zhang, Xiangqun Chen, Xing Xie
2018 arXiv   pre-print
It is hard for humans and algorithms to evaluate the real-time game situation or predict the game result.  ...  In this paper, we introduce MOBA-Slice, a time slice based evaluation framework of relative advantage between teams in MOBA games.  ...  [2] examined the suitability of online reinforcement learning in real-time strategy games with Tank General as early as 2009.  ... 
arXiv:1807.08360v1 fatcat:unm5vo4kkjgnjpn67yvmx5yftm

STARDATA: A StarCraft AI Research Dataset [article]

Zeming Lin, Jonas Gehring, Vasil Khalidov, Gabriel Synnaeve
2017 arXiv   pre-print
We provide full game state data along with the original replays that can be viewed in StarCraft.  ...  The game state data was recorded every 3 frames which ensures suitability for a wide variety of machine learning tasks such as strategy classification, inverse reinforcement learning, imitation learning  ...  All rights reserved. inferred from the replay file; however, reconstructing the full game state requires playback in StarCraft.  ... 
arXiv:1708.02139v1 fatcat:t3qrj3cpd5berpxv3novlmtfc4

Games without Frontiers: Investigating Video Games as a Covert Channel

Bridger Hahn, Rishab Nithyanand, Phillipa Gill, Rob Johnson
2016 2016 IEEE European Symposium on Security and Privacy (EuroS&P)  
We demonstrate the feasibility of this approach by implementing our circumvention scheme over three real-time strategy games (including two best-selling closed-source games).  ...  We evaluate the security of our system prototype, Castle, by quantifying its resilience to a censor-adversary, similarity to real game traffic, and ability to avoid common pitfalls in covert channel design  ...  Acknowlegements This material is based upon work supported by the National Science Foundation under grant numbers CNS-1350720 and CNS-1518845, a Google Faculty Research Award, and an Open Technology Fund  ... 
doi:10.1109/eurosp.2016.17 dblp:conf/eurosp/HahnNGJ16 fatcat:dvpqbamponco7itf4iiwsxpdpy

The Partially Observable Asynchronous Multi-Agent Cooperation Challenge [article]

Meng Yao, Qiyue Yin, Jun Yang, Tongtong Yu, Shengqi Shen, Junge Zhang, Bin Liang, Kaiqi Huang
2021 arXiv   pre-print
Multi-agent reinforcement learning (MARL) has received increasing attention for its applications in various domains.  ...  Inspired from the Wargame, a confrontation game between two armies abstracted from real world environment, we propose the first Partially Observable Asynchronous multi-agent Cooperation challenge (POAC  ...  POCA also provides function to modify the map and game settings by editing json file in code.  ... 
arXiv:2112.03809v1 fatcat:ozbgzhoi45azlpp3a34mbul56i

Team Recommendation Using Order-based Fuzzy Integral and NSGA-II in StarCraft

Lin Wang, Yifeng Zeng, Bilian Chen, Yinghui Pan, Langcai Cao
2020 IEEE Access  
As one of the well-known real-time strategy games, StarCraft has become an important benchmark for game artificial intelligence research.  ...  We use genetic algorithm (GA) to learn the fuzzy measure in the fuzzy integral from the StarCraft replay data and adopt Non-Dominated Sorting Genetic Algorithm (NSGA-II) combined with the fuzzy integral  ...  real-time strategy games.  ... 
doi:10.1109/access.2020.2982647 fatcat:fgg5gpcbkna45dunrcrafalsfa

Skill-Based Differences in Spatio-Temporal Team Behavior in Defence of The Ancients 2 [article]

Anders Drachen, Matthew Yancey, John Maguire, Derrek Chu, Iris Yuhui Wang, Tobias Mahlmann, Matthias Schubert, Diego Klabjan
2016 arXiv   pre-print
Multiplayer Online Battle Arena (MOBA) games are among the most played digital games in the world.  ...  In these games, teams of players fight against each other in arena environments, and the gameplay is focused on tactical combat.  ...  The e-sports environment is being driven primarily by Real-Time Strategy (RTS) games, with StarCraft forming the classic example, and First/Third Person Shooters (FPS, TPS) such as CoD.  ... 
arXiv:1603.07738v1 fatcat:t7pc4irsxvcxzpbax4bljwtu4y

Reinforcement Learning In Two Player Zero Sum Simultaneous Action Games [article]

Patrick Phillips
2021 arXiv   pre-print
strategy.  ...  We first introduce the fundamental concepts of reinforcement learning in two player zero sum simultaneous action games and discuss the unique challenges this type of game poses.  ...  Figure 2 : 2 Policy times Q(s, ·, ·) value matrix in 3-action game. Lowe et al. derive an actor critic method similar to DDPG to learn a policy from this value function in continuous action spaces.  ... 
arXiv:2110.04835v1 fatcat:leyytnerjfaybgx4rxftirknma

Games Without Frontiers: Investigating Video Games as a Covert Channel [article]

Bridger Hahn, Rishab Nithyanand, Phillipa Gill, Rob Johnson
2015 arXiv   pre-print
In this paper, we explore a promising new avenue for covert channels: real-time strategy-video games.  ...  We demonstrate the feasibility of this approach by implementing our coding scheme over two real-time strategy-games (including a very popular closed-source game).  ...  Acknowlegements This material is based in part upon work supported by the National Science Foundation under Grant Number CNS -1350720.  ... 
arXiv:1503.05904v3 fatcat:tfhcbqcvvbgg5kdszladb4tpp4

Skill-based differences in spatio-temporal team behaviour in defence of the Ancients 2 (DotA 2)

Anders Drachen, Matthew Yancey, John Maguire, Derrek Chu, Iris Yuhui Wang, Tobias Mahlmann, Matthias Schubert, Diego Klabajan
2014 2014 IEEE Games Media Entertainment  
Multiplayer Online Battle Arena (MOBA) games are among the most played digital games in the world.  ...  In these games, teams of players fight against each other in arena environments, and the gameplay is focussed on tactical combat.  ...  These games were removed from the dataset. The time ticker in the replay files were standardized to the closest second.  ... 
doi:10.1109/gem.2014.7048109 dblp:conf/gamesem/DrachenYMCWMSK14 fatcat:vtxm2oammfbylo2e2hr5ftdiuq

A Review of Real-Time Strategy Game AI

Glen Robertson, Ian Watson
2014 The AI Magazine  
This literature review covers AI techniques used for real-time strategy video games, focusing specifically on StarCraft.  ...  It finds the industry adoption of academic research is low because it is either in- applicable or too time-consuming and risky to implement in a new game, which highlights an area for potential investi  ...  The other two research areas discussed were noted to be lacking in research contributions, despite being highly appropriate for Real-Time Strategy game research: multi-scale AI, and cooperation.  ... 
doi:10.1609/aimag.v35i4.2478 fatcat:xw7tp4vqvndyle32cyftenp67a

A computer-automated laboratory for studying complex perception-action skills

Ralph J. Roberts, Duncan Brown, Scott Wiebke, Marshall M. Haith
1991 Behavoir research methods, instruments & computers  
In this paper, we describe a computer-based laboratory for collecting and analyzing real-time performance and eye-movement data by using video game-like tasks.  ...  General design considerations are emphasized for solving several of the problems encountered in constructing a real-time data collection system.  ...  The collected data also can be replayed back through the video game by using the replay program.  ... 
doi:10.3758/bf03209990 fatcat:y5yiuav675gyxhexkmoqyo7rqi

What Did I Do Wrong in My MOBA Game? Mining Patterns Discriminating Deviant Behaviours

Olivier Cavadenti, Victor Codocedo, Jean-Francois Boulicaut, Mehdi Kaytoue
2016 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA)  
from the norm that may explain a game outcome from which player can learn more efficient ways of playing.  ...  In this article, we consider Multi-player Online Battle Arena games (MOBA) and particularly, "Defense of the Ancients 2", commonly known simply as DOTA2.  ...  ACKNOWLEDGMENTS This research has been partially funded by the French National Project FUI AAP 14 Tracaverre 2012-2016.  ... 
doi:10.1109/dsaa.2016.75 dblp:conf/dsaa/CavadentiCBK16 fatcat:p3ii5rwdpjhfxheu543lppancu

Decentralized Deep Reinforcement Learning for Network Level Traffic Signal Control [article]

Jin Guo
2020 arXiv   pre-print
In this thesis, I propose a family of fully decentralized deep multi-agent reinforcement learning (MARL) algorithms to achieve high, real-time performance in network-level traffic signal control.  ...  replay, multi-step bootstrapping, etc.  ...  Markov Game Markov game (MG), also known as Stochastic Game, is the extension of MDP in multi-agent environments, with agents interacting with each other to tackle cooperative or competitive tasks (Littman  ... 
arXiv:2007.03433v2 fatcat:zlk4hztww5dctlfdse5fmw5v3m

Interactive record/replay for web application debugging

Brian Burg, Richard Bailey, Andrew J. Ko, Michael D. Ernst
2013 Proceedings of the 26th annual ACM symposium on User interface software and technology - UIST '13  
At most, prior systems demonstrate feasibility by providing a simple VCR-like interface [18, 33] that can record and replay linearly.  ...  In the case of interactive programs, even reproducing a failure can be difficult or impossible: failures can occur on mouse drag events, be time-dependent, or simply occur too infrequently for a developer  ...  ACKNOWLEDGEMENTS This material is based in part upon work supported by the National Science Foundation under Grant Numbers CCF-0952733 and CCF-1153625.  ... 
doi:10.1145/2501988.2502050 dblp:conf/uist/BurgBKE13 fatcat:f3s6knuy4zbsjpzzeevrbs66va
« Previous Showing results 1 — 15 out of 2,702 results