<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel><description>Research Goal: Understanding the computational and statistical principles required to design AI/RL agents.&#xA;Associate Professor at Polytechnique Montréal and Mila. 🇨🇦&#xA;academic.sologen.net</description><link>https://bsky.app/profile/sologen.bsky.social</link><title>@sologen.bsky.social - Amir-massoud Farahmand</title><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mvbpurdmrc2h</link><description>Shana Tova!</description><pubDate>11 Sep 2026 23:29 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mvbpurdmrc2h</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3muzdzxigcc2d</link><description>Nice collection of historic AI-related papers and movies!&#xA;- Minsky&#39;s PhD thesis, which he talks about RL (I&#39;d heard of this; never seen!)&#xA;- Turing&#39;s paper on AI&#xA;- Fukushima&#39;s convolutional net&#xA;- Kismet robot&#xA;&#xA;[contains quote post or other embedded content]</description><pubDate>08 Sep 2026 15:36 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3muzdzxigcc2d</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mux2pym4ec2y</link><description>James R. Munkres, whom I know because of his Topology textbook, has died.&#xA;May he rest connected!&#xA;August 18, 1930 – July 30, 2026&#xA;https://www.douglassfh.com/obituary/james-munkres</description><pubDate>07 Sep 2026 17:44 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mux2pym4ec2y</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mqag6vtv5c2b</link><description>This platform will not replace Twitter/X for us (scientists, researchers, profs, etc.). It might be (noticeably) better in several aspects, but &#xA;(1) it is not a disruptive innovation, and &#xA;(2) has the third mover disadvantage.&#xA;&#xA;P.S: I&#39;ll stay active here for now.</description><pubDate>09 Jul 2026 19:57 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mqag6vtv5c2b</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mqa2vsc5h22n</link><description>It is interesting that we still don&#39;t have a completely clear picture of why/when (Optimisitic) Policy Iteration + Monte Carlo estimate works, especially with every-visit update model (which can be biased though consistent, BTW).</description><pubDate>09 Jul 2026 16:35 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mqa2vsc5h22n</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mplyji3ij22n</link><description>🇨🇦🍁Happy Canada Day!🍁🇨🇦</description><pubDate>01 Jul 2026 16:59 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mplyji3ij22n</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mpf72qpuk22r</link><description>🇨🇦Canadian Heroes🇨🇦</description><pubDate>29 Jun 2026 00:08 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mpf72qpuk22r</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mp55qla3ms2n</link><description>Temporal Difference Learning for Diffusion Models (ICML 2026) arxiv.org/abs/2606.15048 &#xA;By Yangchen Pan (my former PhD student) and co-authors.&#xA;&#xA;It reformulates diffusion training as a Markov reward process and introduces a TD objective to encourage temporal consistency across denoising steps.&#xA;https://arxiv.org/abs/2606.15048</description><pubDate>25 Jun 2026 19:23 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mp55qla3ms2n</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mnl2c4go522b</link><description>Sad to hear the passing of Dimitri Bertsekas (1942- 2026).&#xA;His work has been very influential to me and shaped the way I think about RL. I am sure this is the case for many others in the RL, Control, and Optimization communities.</description><pubDate>05 Jun 2026 21:08 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mnl2c4go522b</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mmfkl3yb4c2z</link><description>If you have a Reinforcement Learning paper accepted at TMLR, JMLR, JAIR, AIJ, or MLJ, you can use this wonderful opportunity to present your work and meet your peers at RLC in Montreal, Canada. 🇨🇦&#xA;&#xA;[contains quote post or other embedded content]</description><pubDate>21 May 2026 23:18 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mmfkl3yb4c2z</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mke2pcsfx225</link><description>Do you use often use PPO, but wish you could use something just better?&#xA;Try REPPO: Relative Entropy Pathwise Policy Optimization!&#xA;Project Page: https://cvoelcker.de/projects/reppo/&#xA;&#xA;[contains quote post or other embedded content]</description><pubDate>25 Apr 2026 22:11 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mke2pcsfx225</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mjschgtbhs2b</link><description>Hypothesis: People have been gradually shifting to write more like ChatGPT and alike.&#xA;They use structures such as &#34;This is not only X; but it is also Y&#34;.&#xA;These struct. are natural part of lang, but either&#xA;1. they&#39;re becoming more prevalent,&#xA;2. I&#39;ve become more sensitive to them.</description><pubDate>18 Apr 2026 20:42 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mjschgtbhs2b</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mifgyjaus22i</link><description>We have a new PhD Candidate in town: @tylerkastner.bsky.social &#xA;Looking forward to all the new work you will be doing on Distributional Reinforcement Learning.</description><pubDate>01 Apr 2026 00:33 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mifgyjaus22i</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mhjoxunwl22y</link><description>Happy Norooz, the Persian new year 1405/2585, the equinox, and the beginning of spring!</description><pubDate>20 Mar 2026 23:42 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mhjoxunwl22y</guid></item><item><link>https://bsky.app/profile/sologen.bsky.social/post/3mfxnrunolc2p</link><description>Ali Khamenei is in hell. The world is a better place now!</description><pubDate>01 Mar 2026 02:07 +0000</pubDate><guid isPermaLink="false">at://did:plc:encka6qjdacjfptucihfrpth/app.bsky.feed.post/3mfxnrunolc2p</guid></item></channel></rss>