原创力文档- 1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
- 2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击 这里二次下载。
- 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
- 4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
- 5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
- 6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
- 7、VIP文档为合作方或网友上传，每下载1次， 网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
Real-Time Neuroevolution in the NERO Video Game
Kenneth O. Stanley (kstanley@)
Bobby D. Bryant (bdbryant@)
Risto Miikkulainen (risto@)
Department of Computer Sciences
University of Texas at Austin
Austin, TX 78712 USA
A version of this paper appears in:
IEEE Transactions on Evolutionary Computation
(Special Issue on Evolutionary Computation and Games),
Vol.9, No. 6, December 2005
Abstract
In most modern video games, character behavior is scripted; no matter how many times the player exploits
a weakness, that weakness is never repaired. Yet if game characters could learn through interacting with
the player, behavior could improve as the game is played, keeping it interesting. This paper introduces the
real-time NeuroEvolution of Augmenting Topologies (rtNEAT) method for evolving increasingly complex
artificial neural networks in real time, as a game is being played. The rtNEAT method allows agents to
change and improve during the game. In fact, rtNEAT makes possible an entirely new genre of video games
in which the player trains a team of agents through a series of customized exercises. To demonstrate this
concept, the NeuroEvolving Robotic Operatives (NERO) game was built based on rtNEAT. In NERO, the
player trains a team of virtual robots for combat against other players’ teams. This paper describes results
from this novel application of machine learning, and demonstrates that rtNEAT makes possible video games
like NERO where agents evolve and adapt in real time. In the future, rtNEAT may allow new kinds of
educational and training applications throu
您可能关注的文档
- Dynamic Bandwidth Management for Single-hop Ad Hoc Wireless Networks：（动态带宽管理单跳特设无线网络）.pdf
- Dynamic taint analysis for automatic detection, analysis, and signature generation of exploits on commodity software：（动态污点分析自动检测、分析和签名代利用商品软件）.pdf
- Dynamics of Random Early Detection：（动态随机早期检测）.pdf
- Economic Performance Through Time：（经济性能通过时间）.pdf
- Effective Erasure Codes for Reliable Computer Communication Protocols：（有效消除代码可靠的计算机通信协议）.pdf
- Effective Upon the Launch of the Computer-based Uniform CPA Examination：（有效的发射计算机统一注册会计师考试）.pdf
- Efficient algorithms for pairing-based cryptosystems：（高效的双线性密码算法）.pdf
- Efficient Crawling Through URL Ordering：（高效的爬行通过URL命令）.pdf
- Efficient Online and Batch Learning using Forward Backward Splitting：（有效的在线学习和批处理使用向前向后分裂）.pdf
- Efficient randomized pattern-matching algorithms：（高效的随机模式匹配算法）.pdf
- Real-Time Obstacle Avoidance for Manipulators and Mobile Robots, Int. Jour of Robotic Research：（机械手和移动机器人实时避障,Int,机器人研究的）.pdf
- Recursive Distributed Representations：（递归的分布式表征）.pdf
- Relative Building-Block Fitness and the Building-Block Hypothesis：（相对积木健身和构建块的假设）.pdf
- Replication Strategies in Unstructured Peer-to-Peer Networks：（在非结构化p2p网络复制策略）.pdf
- Research in Higher Education Journal The Effects of Students’, Page 1：（研究高等教育期刊的影响学生,第1页）.pdf
- Resilient Overlay Networks：（有弹性的覆盖网络）.pdf
- Resource-constrained versus demand-constrained systems：（资源受限与需求约束型系统）.pdf
- REVIEWED：（综述了）.pdf
- Revised calibration of the geomagnetic polarity timescale for the late Cretaceous and Cenozoic：（修改校准的地磁极性晚白垩世和新生代的时间表）.pdf
- Richard Regal：（理查德君威）.pdf
文档评论（0）