🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

There’s still time to apply! ✍️

Please don’t forget to apply for the Black in AI funding for attending this year’s workshop co-located with NeurIPS Conference Deadline is on Oct 3rd. Find more info about this on the latest tweet from BAI pages 😊. Please retweet to help share this to people who might be interested.

I just got officially sponsored to attend NeurIPS Conference in-person thanks to MineRL Project!! I’m so grateful for this opportunity!!! If anyone is attending hit me up we can get a group together!

Ready for #NeurIPS2022?? This year the Competition Track will be both physical and online! We are organizing an in-person session on 29th Nov and virtual workshops with invited speakers and winning teams! Can't wait to finally meet all the organizers in New Orleans! 🎷🎶🎺🎶😍

Then Tim Pearce will discuss imitating human behavior with diffusion models at the Deep RL Workshop: microsoft.com/en-us/research… And I'll share some observations from across these projects in the MineRL Project competition workshop advisor's panel: neurips.cc/virtual/2022/c… [3/4]

We’re presenting on the BASALT competition at NeurIPS Conference today at 6pm CT! Come talk to Brandon, Stephanie Milani, Byron Galbraith, & Anssi about solving hard tasks in Minecraft ⛏ We’re on the second floor in Ballroom C.

Presenting my work for the MineRL BASALT challenge at the NeurIPS workshop tomorrow!

Continuing our industry talks from our co-organizers Microsoft Research and Playing Minecraft with AI with Anssi Kanervisto! #GameAISchool2023 #GameAI

Such a nice conclusion to the MineRL Project competitions to have our paper on the BASALT evaluation & demonstrations datasets accepted as a NeurIPS Conference Datasets & Benchmarks Oral! 🎉 It’s sad to see the competitions go, but we hope that the data & benchmarks will live on.

I’m at NeurIPS Conference! Giving a talk on this work tomorrow at 4:15pm in Ballroom A-C level 2. If you’re interested in RLHF or learning from human feedback more generally (in Minecraft ⛏️), stop by. Also come to our poster at 5pm (#1405, Hall B1+B2)!

Training AI agents from human feedback is critical for safety and alignment. To aid this, we developed two related datasets for Minecraft! 💎 📝 Read our #NeurIPS2023 Datasets & Benchmarks Oral paper: arxiv.org/abs/2312.02405 🧑‍💻 Data & code: github.com/minerllabs/bas… 🧵 1/n

Our paper introduces the BASALT Evaluation & Demonstrations Dataset (BEDD) for learning from human feedback in Minecraft 🛌 We envision that this dataset could be used for both training & evaluating Minecraft AI agents! 3/n

Our work on MineRL Project was featured in this nice article about AI safety! Thanks Kathryn Hulick for speaking with us.

🎉 BEDD has been honored with an Outstanding Paper Award from the ICML MFM-EAI workshop! Grateful to the reviewers & organizers for the opportunity to share our work again. Stop by Lehar 4 on Fri, July 26 at 🕰️ 14:30 for the oral 🕰️ 16:30 for the poster session!

🖤 Thanks for the paper award, ICML2024 MFM-EAI

🎇 I’m on the academic job market! I’m a PhD candidate at Machine Learning Dept. at Carnegie Mellon. My research tackles challenges that arise from the sequential nature of human-AI interaction. Toward this goal, my work involves: 🤖 reinforcement learning, 🧠 foundation models, and 👩‍💻 human-centered AI.

Btw if you’re looking for a difficult benchmark for agents, MineRL Project BASALT is still unsolved 🤖