From eeacaf5babbbe383365cf67a962eeef900df6df9 Mon Sep 17 00:00:00 2001 From: Qihang Zhang Date: Sat, 11 Oct 2025 22:03:42 -0700 Subject: [PATCH 1/3] add initial blog post on Max-Entropy RL and the Boltzmann Distribution --- _posts/2025-10-11-max-ent-rl.md | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 _posts/2025-10-11-max-ent-rl.md diff --git a/_posts/2025-10-11-max-ent-rl.md b/_posts/2025-10-11-max-ent-rl.md new file mode 100644 index 0000000..9f5c619 --- /dev/null +++ b/_posts/2025-10-11-max-ent-rl.md @@ -0,0 +1,18 @@ +--- +layout: distill +title: Why the Exponential? From Max‑Entropy RL to the Boltzmann Distribution +description: This blog post explores why the exponential function appears ubiquitously across modern RL, energy-based modeling, and statistical mechanics. We examine the connection between max-entropy reinforcement learning and the Boltzmann distribution, uncovering the fundamental principles that make the exponential form inevitable and explaining what "temperature" actually does in these frameworks. +tags: reinforcement-learning information-theory boltzmann-distribution +giscus_comments: true +date: 2025-10-11 +featured: true +redirect: https://qihang-zhang.com/Learning-Sys-Blog/2025/10/06/max-ent-rl-and-boltzmann-distribution.html + +authors: + - name: Qihang Zhang + url: "https://qihang-zhang.com/" + affiliations: + name: UBC + +bibliography: 2025-08-18-gen-graph.bib +--- From 72af3791149cd83ed3900322350f17333c699fa9 Mon Sep 17 00:00:00 2001 From: Qihang Zhang Date: Sat, 11 Oct 2025 22:08:58 -0700 Subject: [PATCH 2/3] remove bibliography reference from the Max-Entropy RL blog post --- _posts/2025-10-11-max-ent-rl.md | 1 - 1 file changed, 1 deletion(-) diff --git a/_posts/2025-10-11-max-ent-rl.md b/_posts/2025-10-11-max-ent-rl.md index 9f5c619..3023fb3 100644 --- a/_posts/2025-10-11-max-ent-rl.md +++ b/_posts/2025-10-11-max-ent-rl.md @@ -14,5 +14,4 @@ authors: affiliations: name: UBC -bibliography: 2025-08-18-gen-graph.bib --- From a56d0dc84a2b85df089564c2f212ba361adc56e1 Mon Sep 17 00:00:00 2001 From: Qihang Zhang Date: Sat, 11 Oct 2025 22:18:18 -0700 Subject: [PATCH 3/3] fix indentation in authors section of the Max-Entropy RL blog post --- _posts/2025-10-11-max-ent-rl.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/_posts/2025-10-11-max-ent-rl.md b/_posts/2025-10-11-max-ent-rl.md index 3023fb3..d6a6567 100644 --- a/_posts/2025-10-11-max-ent-rl.md +++ b/_posts/2025-10-11-max-ent-rl.md @@ -9,9 +9,9 @@ featured: true redirect: https://qihang-zhang.com/Learning-Sys-Blog/2025/10/06/max-ent-rl-and-boltzmann-distribution.html authors: - - name: Qihang Zhang - url: "https://qihang-zhang.com/" - affiliations: - name: UBC + - name: Qihang Zhang + url: "https://qihang-zhang.com/" + affiliations: + name: UBC ---