Siddhant Agarwal
54 posts
@agsidd10
PhD CS @UTAustin | Reinforcement Learning & Robotics, prev intern @Amazon
Introducing RLDP – a simple, scalable approach for building strong Behavioral Foundation Models. 🚀 #ICLR2026 ✅ Robust objective: avoids brittle unsupervised RL objectives while staying simple and scalable. 🗂️ No data-coverage limitations: works across a wide variety of datasets. 🧩 One latent space for all tasks: a unified representation space. 🎯➡️🤖 Zero-shot control: specify a reward and directly obtain a policy/behavior – no additional training required.
India should take credit for strengthening hands of Pakistan army. You guys are responsible. Stupid attack on Pakistan in May unleashed by war monger and populist PM Modi to gain votes in Bihar elections followed by applauses has further strengthened its grip on power. Any war, conflict or tension b/w Pakistan and India suit both BJP & Pak Establishment. So keep raising heat and level of threats it ll benefit our army and weaken civilians in Pakistan. If this is purpose of Indian political elite, then let me congratulate as you guys have succeeded in achieving your mission, my friends. Recent Indian attack is another example that has further strengthen Pak Establishment grip on power and weaken Pakistani civilian leaders. Why you lament now to see Pakistan army gaining control and clout in Pakistan.. Perhaps Indians love to deal with Pakistan army generals from Gen Ayub (Lal Bhadur Shastri sb), Gen Zia ( Rajiv sb) to Gen Musharraf ( Vajpayee sb&Manmohan sb) . Indians trust Pakistan Generals more than its prime ministers.
Several of my team members + myself are impacted by this layoff today. Welcome to connect :)
Most assistive robots live in labs. We want to change that. FEAST enables care recipients to personalize mealtime assistance in-the-wild, with minimal researcher intervention across diverse in-home scenarios. 🏆 Outstanding Paper & Systems Paper Finalist @RoboticsSciSys 🧵1/8
We are extending the submission deadline to June 15, 2025 (AoE). Submit your ideas soon!
⚠️ Reminder! Submissions for @RL_Conference's RL beyond Reward Workshop are due May 30 (AoE)! We are brewing an interesting program and seeking innovative research work in reward-free RL. All papers are welcome, from exploratory abstracts to complete research papers.
⚠️ Reminder! Submissions for @RL_Conference's RL beyond Reward Workshop are due May 30 (AoE)! We are brewing an interesting program and seeking innovative research work in reward-free RL. All papers are welcome, from exploratory abstracts to complete research papers.
🤖 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 interpretable link between RL agents and humans and achieving true cross-embodiment transfer.
