Raghu Rajan's Avatar

Raghu Rajan

@raghuspacerajan.bsky.social

PhD / PostDoc in Reinforcement Learning, AutoRL at the University of Freiburg. First author of MDP Playground. Opinions posted here are my own.

103 Followers  |  212 Following  |  2 Posts  |  Joined: 19.11.2024  |  1.5072

Latest posts by raghuspacerajan.bsky.social on Bluesky

Add me please! (I think I wasn't added yet) :)

03.03.2025 21:11 — 👍 0    🔁 0    💬 1    📌 0
2024 in AutoRL TL;DR: From integrating RL with VLMs and LLMs to hyperparameter tuning, environment design, and generalization, 2024 was packed with innovation. We’ve highlighted top advancements in AutoRL and inclu...

Starting the year off with some AutoRL inspiration: the autorl.org team put together our favorite papers on how to make RL work that we found in 2024 - and it's been a pretty great year! 🌟🚀 Let us know what we missed!

autorl.org/blog/retrosp...

16.01.2025 16:15 — 👍 9    🔁 2    💬 1    📌 0
Preview
Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization Zero-shot generalization (ZSG) to unseen dynamics is a major challenge for creating generally capable embodied agents. To address the broader challenge, we start with the simpler setting of contextual...

Our paper "Dreaming of Many Worlds" studied zero-shot generalization in world models for Contextual RL and was later accepted by RLC and EWRL. Here's a thread summarizing the work and putting it in the context in retrospect as ideas for potential future collaborations!

arxiv.org/abs/2403.10967

23.11.2024 12:26 — 👍 62    🔁 8    💬 3    📌 0

Add me please! :)

19.11.2024 11:58 — 👍 1    🔁 0    💬 0    📌 0

@raghuspacerajan is following 20 prominent accounts