I'm at NeurIPS! More importantly, I'll be at the RL Conference social this Wednesday from 7-10 PM at Howling Wolf right by the conference center. Spread the good word.

NeurIPS RL folks, this is tonight. Come hang out with us at Howlin’ Wolf 7-10!

Check out the #NeurIPS2023 workshop on Goal Conditioned Reinforcement Learning: * Tomorrow (Friday) 900 -- 1830 CST * Great speakers: Jeff Clune Reuth Mirsky Olexandr Isayev 🇺🇦🇺🇸 Yonatan Bisk Susan Murphy lab * Program: goal-conditioned-rl.github.io/2023/

Excited to announce our first RLC keynote speaker: Peter Stone!

Turns out offline MARL doesn't just work out of the box. Check out @paulbbarde's 🧵👇 demonstrating why and one possible fix - which he will be presenting at The AAMAS Conference!

The RLC submission page is now open! Get your submissions ready: openreview.net/group?id=rl-co…

Still using one-step dynamics model for model-based RL? Check out our work on Diffusion World Model, which is outperforming one-step models by 44% for offline D4RL tasks arxiv.org/abs/2402.03570 joint work w/ Zihan Ding, Amy Zhang Yuandong Tian [1/3]

The 3rd RLC keynote speaker is Doina Precup! She's been a major influence in so many parts of RL and we could not be more excited for her talk

Excited to announce the call for workshop proposals for RL_Conference is open! rl-conference.cc/call_for_works… Due March 8th. Josiah Hanna and I are the workshop co-chairs this year and we hope you'll consider submitting a proposal. Workshops on any RL-related topics are welcome!

A friendly reminder: two weeks until the RLC 2024 submission deadline!

To accommodate nearby conferences and deadlines yet still maintain good reviewer matching, 𝐰𝐞 𝐚𝐫𝐞 𝐞𝐱𝐭𝐞𝐧𝐝𝐢𝐧𝐠 𝐭𝐡𝐞 𝐟𝐮𝐥𝐥 𝐩𝐚𝐩𝐞𝐫 𝐝𝐞𝐚𝐝𝐥𝐢𝐧𝐞 𝐭𝐨 𝐌𝐚𝐫𝐜𝐡 𝟖𝐭𝐡 but keeping March 1st as the abstract deadline

I did an interview on YouTube for ML New Papers. Lots of fun with Charles Riou talking about research, RL and networking in ML. Check out the video below.

As part of putting together #RLC2024, we spent a bunch of time thinking about how best to improve the review process for an ML conference. Post decisions, we spent some time reflecting on what went well and what we want to change in the future: check out rl-conference.cc/blogs/review_p…!

Given the community response to RLC 2024, we're excited to start planning for RLC 2025. If you're interested in organizing or hosting, fill out this link: forms.gle/c9QcUdbKeXakd5…

A new self-supervised reinforcement learning objective that learns a basis set for the optimal Q of any reward function. Check out Siddhant Agarwal @ RLC 2025’s thread below!

📢Come to check our #NeurIPS2024 paper on how to correctly use diffusion models in RL! We rethink diffusion-based RL algorithms by using a guide-then-select paradigm to bring minimal out-of-distribution errors. Project page: ryanxhr.github.io/Diffusion-DICE/

🤖 Introducing RL Zero 🤖: a new approach to transform language into behavior zero-shot for embodied agents without labeled datasets! RL Zero enables prompt-to-policy generation, and we believe this unlocks new capabilities in scaling up language-conditioned RL, providing an

Unleashing the power of unordered particles: **EC-Diffuser** leverages a novel Transformer-based diffusion denoiser to learn goal-conditioned multi-object manipulation policy from pixels, achieving zero-shot generalization!👇 #ICLR2025 #diffusion #Transformers

Looking forward to #ICML2025! Ben Eysenbach and I will be giving a tutorial on RL meets GenAI tomorrow. Consider coming!

VERY excited for RL_Conference next week, especially RL Beyond Rewards Workshop on Tuesday! There will be a social that evening, register here: lu.ma/jaeclqge. Hope to see you there! Harshit Sikchi (at RLC 25) Max Rudolph Pranaya Jajoo Siddhant Agarwal @ RLC 2025