Artificial IntelligenceArtificial intelligence, including machine learning, has emerged as a transformational science and engineering discipline. Artificial Intelligence: Foundations of Computational Agents presents AI using a coherent framework to study the design of intelligent computational agents. By showing how the basic approaches fit into a multidimensional design space, readers learn the fundamentals without losing sight of the bigger picture. The new edition also features expanded coverage on machine learning material, as well as on the social and ethical consequences of AI and ML. The book balances theory and experiment, showing how to link them together, and develops the science of AI together with its engineering applications. Although structured as an undergraduate and graduate textbook, the book's straightforward, self-contained style will also appeal to an audience of professionals, researchers, and independent learners. The second edition is well-supported by strong pedagogical features and online resources to enhance student comprehension. |
Contents
Agent Architectures and Hierarchical Control | 49 |
Reasoning Planning and Learning with Certainty | 75 |
Reasoning with Constraints | 125 |
Propositions and Inference | 173 |
Planning with Certainty | 239 |
Supervised Machine Learning | 267 |
Reasoning Learning and Acting with Uncertainty | 341 |
Planning with Uncertainty | 425 |
Learning to Act | 549 |
Reasoning Learning and Acting with Individuals and Rela | 579 |
Ontologies and KnowledgeBased Systems | 645 |
Relational Planning Learning and Probabilistic Reasoning | 691 |
Retrospect and Prospect | 731 |
A Mathematical Preliminaries and Notation | 745 |
References | 751 |
| 773 | |
Other editions - View all
Artificial Intelligence: Foundations of Computational Agents David L. Poole,Alan K. Mackworth Limited preview - 2010 |
Common terms and phrases
able action agent algorithm allow answer assignment assume atom belief better building called carried Chapter choose clause coffee complexity conditional Consider consistent constraints cost decision tree defined definite depends derived designer determine distribution domain effect environment error example Exercise factor false Figure frontier function give given goal graph heuristic individuals initial input intelligent interpretation knowledge base layer learning linear live logical means method minimal node observed optimal particular path position possible prediction preferences probability problem procedure proof proposition pruning query question random reasoning relations represent representation result reward robot rule samples selected shows solution solve space specifies step strategy student Suppose symbols task true utility variable weights