Reinforcement_Learning
Reinforcement Learning 豆瓣
作者: Richard S. Sutton / Andrew G. Barto The MIT Press 1998 - 3
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.
The Hippocampus Book 豆瓣
作者: Andersen, Per (EDT)/ Morris, Richard (EDT)/ Amaral, David (EDT)/ Bliss, Tim (EDT)/ O'Keefe, John (EDT) Oxford University Press 2006 - 11
The hippocampus is one of a group of remarkable structures embedded within the medial temporal lobe of the brain. Long known to be important for memory, it has been a prime focus of neuroscience research for many years. The Hippocampus Book promises to facilitate developments in the field in a major way by bringing together, for the first time, contributions by leading international scientists working on hippocampal anatomy, physiology, and function. This authoritative volume offers the most comprehensive, up-to-date account of what the hippocampus does, how it does it and what happens when things go wrong. At the same time, it illustrates how research focusing on this single brain structure has revealed principles of wider generality for the whole brain in relation to anatomical connectivity, synaptic plasticity, cognition and behaviour, and computational algorithms. Well-organised in its presentation of both theory and experimental data, this peerless work vividly illustrates the astonishing progress that has been made in unravelling the workings of the brain. The Hippocampus Book is destined to take a central place on every neuroscientist's bookshelf.