I'm happy to share that our Time-Aware World Model (TAWM) has been accepted to #ICML2025! 🎆 By conditioning world model on time steps, we can train a policy that adapts to varying observation frequencies as shown below 👇 (note that TAWM-based policy successfully closes the box

✨Introducing SENSEI✨ We bring semantically meaningful exploration to model-based RL using VLMs. With intrinsic rewards for novel yet useful behaviors, SENSEI showcases strong exploration in MiniHack, Pokémon Red & Robodesk. Accepted at ICML 2025🎉 Joint work with Christian Gumbsch 🧵

I'll be giving a talk at this exciting workshop tomorrow at ICML and a panel after (with great panelists). Please stop by and say hello! #ICML2025

Are you a strong builder - of software, of community, of the future of open source AI? We're hiring software engineers, DevRel, & more mozilla.ai! Join a growing, well-funded, mission-driven team 🦊 building a sustainable open source future. Link: mozilla.ai/careers

PufferLib has won a best paper award for resourcefulness in reinforcement learning! Thank you to our entire open-source community + of course Spencer Spencer Cheng, who has built more of the environments than anyone else! Come chat with us in person today/tomorrow!

It was an honor to receive the Outstanding Paper Award on Tooling, Environments, and Evaluation in Reinforcement Learning for Syllabus! Come see my talk today at 10:20am in room CCIS 1-140 or check out our poster (#29) at 3pm!

E69: Outstanding Paper Award Winners 1/2 RL_Conference 2025 Alex Goldie @ RLC 25 : How Should We Meta-Learn Reinforcement Learning Algorithms? Ryan Sullivan : Syllabus: Portable Curricula for Reinforcement Learning Agents Joseph Suarez 🐡 : PufferLib 2.0: Reinforcement Learning at 1M

Finally there’s an efficient library for UED algs which doesn’t require Jax-accelerated environments. Great to have more options for UED researchers to supliment minimax and jaxUED. Also includes Robust PLR, SFL, and OMNI

This was a fun collaboration! Tdlr: ReAct is not all you need -- priming LMs to reason/plan intermittently in agentic tasks can improve the sample efficiency of multi-step RL Bonus: LM agents trained with this recipe can be steered with human-written plans at test-time