Artificial Intelligence: Foundations of Computational Agents
Recent decades have witnessed the emergence of artificial intelligence as a serious science and engineering discipline. Artificial Intelligence: Foundations of Computational Agents is a textbook aimed at junior to senior undergraduate students and first-year graduate students. It presents artificial intelligence (AI) using a coherent framework to study the design of intelligent computational agents. By showing how basic approaches fit into a multidimensional design space, readers can learn the fundamentals without losing sight of the bigger picture. The book balances theory and experiment, showing how to link them intimately together, and develops the science of AI together with its engineering applications. Although structured as a textbook, the book's straightforward, self-contained style will also appeal to a wide audience of professionals, researchers, and independent learners. AI is a rapidly developing field: this book encapsulates the latest results without being exhaustive and encyclopedic. It teaches the main principles and tools that will allow readers to explore and learn on their own. The text is supported by an online learning environment, artint.info, so that students can experiment with the main AI algorithms plus problems, animations, lecture slides, and a knowledge representation system for experimentation and problem solving.
What people are saying - Write a review
We haven't found any reviews in the usual places.
action agent algorithm answer Artiﬁcial assignment assume atom base-level belief network branching factor choose classiﬁer coffee conditional probability Consider constraints cost decision network decision tree deﬁned deﬁnite clause delivery robot denotes depends derived difﬁcult domain efﬁcient environment error Exercise factor Figure ﬁnd ﬁnding ﬁnite ﬁrst ﬁt ﬁxed frontier function give given goal node graph heuristic hypothesis individuals inﬁnite input features intelligent intended interpretation iteration knowledge base language learning linear means meta-interpreter minimal Nash equilibrium negation as failure observed ontology optimal policy outcome path possible worlds posterior probability prediction probability distribution problem proof procedure proposition pruning pseudocount Q-learning query random variable reasoning reinforcement learning relation represent representation reward robot sample satisﬁes semantics sensor solution solve speciﬁes step strategy student supervised learning Suppose switch symbols tion training examples update utility