<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Composition | Steve James</title><link>https://sdjames.me/tag/composition/</link><atom:link href="https://sdjames.me/tag/composition/index.xml" rel="self" type="application/rss+xml"/><description>Composition</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Wed, 01 Jul 2026 00:00:00 +0000</lastBuildDate><image><url>https://sdjames.me/media/icon_huf407e28faea15ab880cdbc1ef97b5c3b_31359_512x512_fill_lanczos_center_3.png</url><title>Composition</title><link>https://sdjames.me/tag/composition/</link></image><item><title>Weighted Composition for Entropy-regularised Reinforcement Learning</title><link>https://sdjames.me/publication/nyabadza-2026-weighted/</link><pubDate>Wed, 01 Jul 2026 00:00:00 +0000</pubDate><guid>https://sdjames.me/publication/nyabadza-2026-weighted/</guid><description/></item><item><title>Compositional Instruction Following with Language Models and Reinforcement Learning</title><link>https://sdjames.me/publication/cohen-2024-compositional/</link><pubDate>Sun, 01 Dec 2024 00:00:00 +0000</pubDate><guid>https://sdjames.me/publication/cohen-2024-compositional/</guid><description/></item><item><title>End-to-End Learning to Follow Language Instructions with Compositional Policies</title><link>https://sdjames.me/publication/cohen-2022-end/</link><pubDate>Wed, 14 Dec 2022 00:00:00 +0000</pubDate><guid>https://sdjames.me/publication/cohen-2022-end/</guid><description/></item><item><title>Skill Machines: Temporal Logic Composition in Reinforcement Learning</title><link>https://sdjames.me/publication/nangue-2022-skill-b/</link><pubDate>Fri, 09 Dec 2022 00:00:00 +0000</pubDate><guid>https://sdjames.me/publication/nangue-2022-skill-b/</guid><description/></item><item><title>Facilitating Safe Sim-to-Real through Simulator Abstraction and Zero-shot Task Composition</title><link>https://sdjames.me/publication/love-2022-facilitating/</link><pubDate>Sun, 23 Oct 2022 00:00:00 +0000</pubDate><guid>https://sdjames.me/publication/love-2022-facilitating/</guid><description/></item><item><title>Skill Machines: Temporal Logic Composition in Reinforcement Learning</title><link>https://sdjames.me/publication/nangue-2022-skill-a/</link><pubDate>Sun, 23 Oct 2022 00:00:00 +0000</pubDate><guid>https://sdjames.me/publication/nangue-2022-skill-a/</guid><description/></item><item><title>Learning to Follow Language Instructions with Compositional Policies</title><link>https://sdjames.me/publication/cohen-2021-learning/</link><pubDate>Thu, 04 Nov 2021 00:00:00 +0000</pubDate><guid>https://sdjames.me/publication/cohen-2021-learning/</guid><description/></item><item><title>Composing Value Functions in Reinforcement Learning</title><link>https://sdjames.me/publication/van-2019-composing/</link><pubDate>Mon, 10 Jun 2019 00:00:00 +0000</pubDate><guid>https://sdjames.me/publication/van-2019-composing/</guid><description/></item><item><title>Will it Blend? Composing Value Functions in Reinforcement Learning</title><link>https://sdjames.me/publication/van-2018-will/</link><pubDate>Sat, 14 Jul 2018 00:00:00 +0000</pubDate><guid>https://sdjames.me/publication/van-2018-will/</guid><description/></item></channel></rss>