游戲ai介紹(doc)-資料下載頁
2025-06-25 03:19本頁面
【正文】 進(jìn)行攻擊。Effective and efficient pathfinding is a fundamental task that nonplayer characters must acplish in all sorts of games. Nonplayer character units in a war simulation must be able to navingate over terrain an aviod barriers to reach the in a firstperson shooter must be able to navigate through dungeons or buildings to reach or escape from the player. The scenarios are endless, and it39。s no wonder that AI developers give pathfinding tremendous attention. These are only a few of the established game AI techniques。 others include scripting, rulesbased systems, and some artificial life(Alife) techniques, to name a few. 在各種各樣都的游戲中，高效的尋路是機(jī)器方要完成的一個基礎(chǔ)的任務(wù)。在一個戰(zhàn)爭策略游戲中，一個機(jī)器方單位需要完成越過地形和躲避障礙物去接近敵人的一個行為。在一個第一人稱射擊類游戲中，被射擊者需要穿過地牢或建筑以完成接近或逃避玩家控制的人物的行為。這種腳本情節(jié)是非常多的，難怪AI開發(fā)人員對尋路算法給予了極大關(guān)注。這些只是游戲AI技術(shù)的一小部分，其他技術(shù)還包括插入腳本，規(guī)則系統(tǒng)和一些智能生命技術(shù)，等等。Alife techniques are mon in robotic applications, and developers have adapted and used them with great success in video games. Basically, an Alife system is a synthetic system that exhibits natural behaviors. These behaviors are emergent and develop as a result of the bined effect of lowerlevel algorithms.生命技術(shù)在機(jī)器人應(yīng)用程序中是很普遍的，開發(fā)人員已經(jīng)在視頻游戲中改編和使用機(jī)器人，并且取得了巨大的成功?；旧?，一個生命系統(tǒng)是一個綜合系統(tǒng)，具有自然的行為。這些行為作為一底層算法的綜合效應(yīng)的新興和發(fā)展的結(jié)果。The Future of Game AI游戲AI的展望The next big thing in game AI is learning. The game should evolve, learn, and adapt the more it39。s played. The techniqiues for learning and reacting to character behavior fall under the nondeterministic. Specifically, such nondeterministic, learning AI techniques take longer to develop and test. Further, it39。s more difficult to really understand what the AI is doing, which makes debugging more difficult. These factors have proven to be serious barriers for widespread use of learning AI techniques.在游戲AI中，下一件大事就是學(xué)習(xí)。游戲更應(yīng)是在玩的時候進(jìn)化、學(xué)習(xí)和適應(yīng)。角色的學(xué)習(xí)和反應(yīng)行為屬于非定性的技術(shù)。具體而言，這種不確定性，使學(xué)習(xí)AI技術(shù)需要更長的時間來開發(fā)和測試。此外，它讓人更難以真正理解AI究竟在做什么，這使得調(diào)試更加困難。這些因素已被證明是廣泛使用和學(xué)習(xí)AI技術(shù)的嚴(yán)重障礙。Several mainstream games, such as Creatures, Black amp。 White, Battlecruiser 3000 AD, Dirt Track Racing,Fields of Battle,and Heavy Gear, used nonderterministic AI success sparked a renewed interest in learning AI methods such as decision trees, neural networds, genetic algorithms, and probabilistic methods.幾種主流的游戲，如利用非定性AI方法的生物，黑與白，巡洋艦3000 AD，泥地賽車，野外戰(zhàn)場和重裝機(jī)甲。這些游戲的成功引發(fā)了新的學(xué)習(xí)AI方法的興趣，如決策樹算法、神經(jīng)網(wǎng)絡(luò)算法、遺傳算法和概率的方法。These successful games use nondeterministic methods in conjunction with more traditional deterministic methods, and use them only where they are needed and only for problems for which they are best suited. A neural netwoek is not a magic pill that will solve all AI problems in a games。 however, you can use it with impressive results for very specific具體的AI 任務(wù)tasks within a hybrid AI system. This is the approach we advocate for using these nondeterministic this way,you can at least isolate the parts of your AI that are unpredictable and more difficult to develop ,test,and debug,while ideally keeping the majority of your AI system in tranditional form.這些成功的游戲使用非定性方法與更傳統(tǒng)的定性方法結(jié)合起來，并將這些方法只用在需要的地方，并且與唯一問題形成最佳匹配。一個神經(jīng)網(wǎng)絡(luò)算法不是靈丹妙藥，不可能解決一個游戲AI中的所有問題；然而，你可以在一個混合的AI系統(tǒng)中使用令人印象深刻的結(jié)果去完成非常具體的AI任務(wù) 。這一方法我們提倡使用非定性方法。這樣，你至少能把你的AI中不可預(yù)測的和更難以開發(fā)、測試和調(diào)試的那些部分分離開來，同時理想地以傳統(tǒng)的形式保持你的AI系統(tǒng)的大部分。9
高考資料相關(guān)推薦
鄂ICP備17016276號-1