<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Books on Marc G. Bellemare</title><link>https://marcgbellemare.info/en/books/</link><description>Recent content in Books on Marc G. Bellemare</description><generator>Hugo</generator><language>en</language><copyright>© {year} Marc G. Bellemare</copyright><lastBuildDate>Tue, 30 May 2023 00:00:00 +0000</lastBuildDate><atom:link href="https://marcgbellemare.info/en/books/index.xml" rel="self" type="application/rss+xml"/><item><title>Distributional Reinforcement Learning</title><link>https://marcgbellemare.info/en/books/distributional-rl/</link><pubDate>Tue, 30 May 2023 00:00:00 +0000</pubDate><guid>https://marcgbellemare.info/en/books/distributional-rl/</guid><description>&lt;p&gt;&lt;strong&gt;Marc G. Bellemare, Will Dabney, Mark Rowland&lt;/strong&gt;
MIT Press, May 2023 · 384 pages · Adaptive Computation and Machine Learning series&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;&lt;a href="https://mitpress.mit.edu/9780262048019/distributional-reinforcement-learning/"&gt;MIT Press page&lt;/a&gt;&lt;/li&gt;
&lt;li&gt;&lt;a href="https://www.distributional-rl.org/"&gt;Book website&lt;/a&gt;&lt;/li&gt;
&lt;li&gt;&lt;a href="https://direct.mit.edu/books/oa-monograph/5590/Distributional-Reinforcement-Learning"&gt;Open-access PDF&lt;/a&gt;&lt;/li&gt;
&lt;li&gt;ISBN (hardcover): 9780262048019 · ISBN (eBook): 9780262374019&lt;/li&gt;
&lt;/ul&gt;
&lt;hr&gt;
&lt;p&gt;This is the first comprehensive guide to distributional reinforcement learning, providing a new mathematical formalism for thinking about decisions from a probabilistic perspective. Rather than computing expected values, the book focuses on how total reward behaves as a probability distribution — presenting core concepts, mathematical proofs, and algorithmic developments for characterising, computing, estimating, and making decisions based on random returns. Applications span finance, computational neuroscience, psychology, macroeconomics, and robotics.&lt;/p&gt;</description></item></channel></rss>