Libros de Informática práctica, página 20 de 348

Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment.In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning.Their discussion ranges from the history of the field''s intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts.Part I defines the reinforcement learning problem in terms of Markov decision processes.Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning.Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.

This book focuses on the tips and techniques used to identify the symptoms and determine possible causes of lousy network performance using Wireshark, the world''s most popular network analyzer.Check out the Table of Contents in the Preview Pages section to the right to view the numerous skills and labs contained in this book. Order the book and jump directly to a skill you wish to master, or follow along from start to end to gradually enhance your Wireshark network troubleshooting capabilities.

La finalidad de este texto es que el lector aprenda los principios de diseño e implementación de la organización y arquitectura de los computadores actuales. Por consiguiente, un tratamiento puramente conceptual o teorico seria inadecuado. Este libro utiliza ejemplos de muchas maquinas diferentes para clarificar y reforzar los conceptos presentados. Muchos, pero no todos, de los ejemplos se han ideado a partir de dos familias de computadores: Intel Pentium 4 y PowerPC IBM/Freescale. Estos dos sistemas juntos abarcan la mayoria de las tendencias en diseño de lso computadores de hoy en dia. El Pentium 4 es esencialmente un computador con un conjunto complejo de instrucciones (CISC, Complex Instruction Set Computer) con caracteristicas RISC, mientras que el PowerPC es esencialmente un computador con un conjunto reducido de instrucciones. Ambos sistemas utilizan principio de diseño superescalar yambos soportan configuraciones multiprocesador.