The first comprehensive guide to distributional reinforcement learning, providing a new mathematical formalism for thinking about decisions from a probabilistic perspective.
Distributional reinforcement learning is a new mathematical formalism for thinking about decisions. Going beyond the common approach to reinforcement learning and expected values, it focuses on the total reward or return obtained as a consequence of an agent's choices—specifically, how this return behaves from a probabilistic perspective. In this first comprehensive guide to distributional reinforcement learning, Marc G. Bellemare, Will Dabney, and Mark Rowland, who spearheaded development of the field, present its key concepts and review some of its many applications. They demonstrate its power to account for many complex, interesting phenomena that arise from interactions with one's environment.
The authors present core ideas from classical reinforcement learning to contextualize distributional topics and include mathematical proofs pertaining to major results discussed in the text. They guide the reader through a series of algorithmic and mathematical developments that, in turn, characterize, compute, estimate, and make decisions on the basis of the random return. Practitioners in disciplines as diverse as finance (risk management), computational neuroscience, computational psychiatry, psychology, macroeconomics, and robotics are already using distributional reinforcement learning, paving the way for its expanding applications in mathematical finance, engineering, and the life sciences. More than a mathematical approach, distributional reinforcement learning represents a new perspective on how intelligent agents make predictions and decisions.
"synopsis" may belong to another edition of this title.
Marc G. Bellemare is Senior Staff Research Scientist, Google Research and Adjunct Professor, McGill University. Will Dabney is Senior Staff Research Scientist, DeepMind. Mark Rowland is Senior Research Scientist, DeepMind.
"About this title" may belong to another edition of this title.
Seller: Michener & Rutledge Booksellers, Inc., Baldwin City, KS, U.S.A.
Hardcover. Condition: As New. Text clean and tight; no dust jacket; Adaptive Computation And Machine Learning; 8vo 8" - 9" tall; 384 pages. Seller Inventory # 249503
Seller: AMM Books, Gillingham, KENT, United Kingdom
hardcover. Condition: Very Good. In stock ready to dispatch from the UK. Seller Inventory # mon0000303896
Quantity: 1 available
Seller: GreatBookPrices, Columbia, MD, U.S.A.
Condition: New. Seller Inventory # 44779722-n
Seller: Books Puddle, New York, NY, U.S.A.
Condition: New. Seller Inventory # 26395244992
Seller: PBShop.store UK, Fairford, GLOS, United Kingdom
HRD. Condition: New. New Book. Shipped from UK. Established seller since 2000. Seller Inventory # GB-9780262048019
Quantity: 2 available
Seller: Speedyhen LLC, Hialeah, FL, U.S.A.
Condition: NEW. Seller Inventory # NWUS9780262048019
Seller: Rarewaves.com USA, London, LONDO, United Kingdom
Hardback. Condition: New. Seller Inventory # LU-9780262048019
Quantity: 1 available
Seller: Majestic Books, Hounslow, United Kingdom
Condition: New. Seller Inventory # 402213407
Quantity: 1 available
Seller: GreatBookPrices, Columbia, MD, U.S.A.
Condition: As New. Unread book in perfect condition. Seller Inventory # 44779722
Seller: SMASS Sellers, IRVING, TX, U.S.A.
Condition: New. Brand New Original US Edition. Customer service! Satisfaction Guaranteed. Seller Inventory # ASNNN-2419