news | Benjamin Eysenbach

Nov 22, 2024	Princeton RL @ NeurIPS 2024! Some say ``hi’’ and check out the work below! Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference. With Vivek Myers. Poster at 7:30pm on Wed Dec 11. Learning to Assist Humans without Inferring Rewards. With Evan Ellis and Vivek Myers. Poster at 2:00pm on Thur Dec 12. A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals. Led by Grace Liu and Michael Tang. Intrinsically-Motivated and Open-Ended Learning Workshop. Oral prentation on 2:45pm – 3:00pm on Sunday Dec 15. Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning. Led by Chongyi Zheng and Jens Tuyls. Intrinsically-Motivated and Open-Ended Learning Workshop. Poster at 10:30am – 11:30am and 3:pm – 4pm on Sunday Dec 15.
Sep 13, 2024	JaxGCRL: A new benchmark for goal-conditioned RL is blazing fast, allowing you to train at 1 million steps per minute on 1 GPU. Experiments run so fast that the algorithm design process becomes interactive. Tools like this not only make research much more accessible (e.g., you can now run a bunch of interesting experiments in a free Colab notebook before the 90 min timeout), but also will change how RL is taught (less fighting with dependencies, more experiments on complex tasks, less waiting for experiments to queue and finish); stay tuned for COS 435 this Spring!
Sep 12, 2024	Upcoming talks: NYU GRAIL (Oct 2, 2024). Facebook – Reasoning and Planning (Oct 8, 2024). Colloquium at Queens College (Oct 21, 2024). European Workshop on RL: Keynote (Oct 28, 2024).
Aug 13, 2024	Skills and directed exploration seem to emerge from contrastive RL! Check out the website for videos, code, and the full paper! Let by Grace Liu with Michael Tang.
Aug 9, 2024	In attempts to change perceptions about who does RL, we’ve put together a poster of Notable Women in RL!
Jul 1, 2024	Excited to share work that will be presented at ICML 2024! A Rate-Distortion View of Uncertainty Quantification. Work led by Ifigeneia Apostolopoulou. Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making. Work led by Vivek Myers. [Code] Learning to Assist Humans without Inferring Rewards. Work led by Vivek Myers and Evan Ellis. At the ICML 2024 Workshop on Models of Human Feedback for AI Alignment.
May 1, 2024	Fall 2024 I’ll be teaching an independent work seminar on unsupervised RL (COS 397-S06 for juniors, COS 497-S06 for seniors). If interested, please join the waitlist.
Apr 1, 2024	Excited to share work that will be presented at ICLR 2024! Contrastive Difference Predictive Coding. Work led by Chongyi Zheng. Website with videos and code. Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data. Work led by Chongyi Zheng. Website with videos and code. (Spotlight! <5%) Bridging State and History Representations: Understanding Self-Predictive RL. Work led by Tianwei Ni. Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View. Work led by Raj Ghugare. Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations. Work led by Yongyuan Liang.
Mar 11, 2024	New paper on planning by interpolation! With Vivek Myers.
Jan 1, 2024	Spring 2024 I’ll be teaching the new undergraduate Introduction to RL (COS 435 / ECE 433), together with Mengdi Wang!