- 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
knowledge-gathering agents in adventure games(避免主观偏见的代理冒险游戏)
Knowledge-Gathering Agents in Adventure Games
Brian Hlubocky and Eyal Amir
Computer Science Department
University of Illinois at Urbana-Champaign
Urbana, IL 61801, USA
{hlubocky,eyal}@
Abstract tially nondeterministic world, with an extremely large state
space (greater than 240 states). This renders unusable tradi-
Computer text-based adventure games are virtual tional planning and learning algorithms, such as reinforce-
worlds in which humans or artificial agents act to- ment learning [Kaelbling et al., 1996] and POMDPs. New
wards a specified goal through a text-based inter- algorithms for tracking the world, learning, and exploration
face. In this paper we describe progress towards are required.
an agent that can interact with a game world in
In this paper, we describe our experiences, including cur-
a human-like fashion. Precisely, we present the
rent progress and difficulties encountered in creating an intel-
first accurate knowledge-gathering software agent
that can track the state of the world in a text- ligent agent that plays computer text-based adventure games.
Currently, our age
您可能关注的文档
- getting to scale with good educational practice(量表具有良好的教育实践).pdf
- given that the local land services combines the former livestock health and pest and(考虑到当地的土地结合前家畜健康和害虫和服务).pdf
- genetic algorithms in noisy environments(遗传算法在嘈杂的环境中).pdf
- going-concern opinions in the "new" legal environment(在u201c持续经营意见;new"法律环境).pdf
- gossip-based computation of aggregate information(gossip-based计算的聚合信息).pdf
- governor advisory on(行长咨询).pdf
- gps-free positioning in mobile ad hoc networks(gps-free移动ad hoc网络中定位).pdf
- graphical fisheye views of graphs(图的图形鱼眼的观点).pdf
- grammatical category disambiguation by statistical optimization(语法类别统计优化消歧).pdf
- guidelines for evaluating and expressing the uncertainty of nist measurement results(评估指南和表达nist测量结果的不确定性).pdf
- laplace’s demon and the adventures of his apprentices(拉普拉斯的魔鬼和他的学徒的冒险).pdf
- large-scale named entity disambiguation based on wikipedia data(大规模的命名实体消歧基于维基百科的数据).pdf
- large-sample standard(大样本标准).pdf
- leadership, experience, adventure, friendship(领导下,经验,冒险,友谊).pdf
- learning to construct knowledge bases from the world wide web(学习从万维网构建知识库).pdf
- learning to parse natural language with maximum entropy models(学习与最大熵模型来解析自然语言).pdf
- learner motivation assessment with <e-adventure> game platform(学习者动机与评估& lt;e-adventure>游戏平台).pdf
- least-squares policy iteration(最小二乘迭代策略).pdf
- level-spacing distributions and the airy kernel(能级间距分布和空气的内核).pdf
- limited information estimators and exogeneity tests for simultaneous probit models(有限的信息估计和exogeneity测试同步概率单位模型).pdf
文档评论(0)