Reinforcement Learning
Richard S. Sutton
dec. 2012 · The Springer International Series in Engineering and Computer Science Bog 173 · Springer Science & Business Media
5,0star
1 anmeldelsereport
E-bog
172
Sider
reportBedømmelser og anmeldelser verificeres ikke Få flere oplysninger
Om denne e-bog
Reinforcement learning is the learning of a mapping from situations to actions so as to maximize a scalar reward or reinforcement signal. The learner is not told which action to take, as in most forms of machine learning, but instead must discover which actions yield the highest reward by trying them. In the most interesting and challenging cases, actions may affect not only the immediate reward, but also the next situation, and through that all subsequent rewards. These two characteristics -- trial-and-error search and delayed reward -- are the most important distinguishing features of reinforcement learning.
Reinforcement learning is both a new and a very old topic in AI. The term appears to have been coined by Minsk (1961), and independently in control theory by Walz and Fu (1965). The earliest machine learning research now viewed as directly relevant was Samuel's (1959) checker player, which used temporal-difference learning to manage delayed reward much as it is used today. Of course learning and reinforcement have been studied in psychology for almost a century, and that work has had a very strong impact on the AI/engineering work. One could in fact consider all of reinforcement learning to be simply the reverse engineering of certain psychological learning processes (e.g. operant conditioning and secondary reinforcement).
Reinforcement Learning is an edited volume of original research, comprising seven invited contributions by leading researchers.
Reinforcement learning is both a new and a very old topic in AI. The term appears to have been coined by Minsk (1961), and independently in control theory by Walz and Fu (1965). The earliest machine learning research now viewed as directly relevant was Samuel's (1959) checker player, which used temporal-difference learning to manage delayed reward much as it is used today. Of course learning and reinforcement have been studied in psychology for almost a century, and that work has had a very strong impact on the AI/engineering work. One could in fact consider all of reinforcement learning to be simply the reverse engineering of certain psychological learning processes (e.g. operant conditioning and secondary reinforcement).
Reinforcement Learning is an edited volume of original research, comprising seven invited contributions by leading researchers.
Bedømmelser og anmeldelser
5,0
1 anmeldelse
Bedøm denne e-bog
Fortæl os, hvad du mener.
Oplysninger om læsning
Smartphones og tablets
Installer appen Google Play Bøger til Android og iPad/iPhone. Den synkroniserer automatisk med din konto og giver dig mulighed for at læse online eller offline, uanset hvor du er.
Bærbare og stationære computere
Du kan høre lydbøger, du har købt i Google Play via browseren på din computer.
e-læsere og andre enheder
Hvis du vil læse på e-ink-enheder som f.eks. Kobo-e-læsere, skal du downloade en fil og overføre den til din enhed. Følg den detaljerede vejledning i Hjælp for at overføre filerne til understøttede e-læsere.
