Post by Ahmed H. Qureshi

We recently had eight new papers accepted: 3 at #ICLR2026 and 5 at #ICRA2026, spanning quasimetric and multi-agent reinforcement learning, PDE-driven learning for motion planning, Hamilton–Jacobi reachability, and diffusion-based policies for robotics. 1. Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learning w/ Vittorio Giammarino https://lnkd.in/grkJbQK2 ICLR 2. Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning w/ Xuefeng Wang, Lei Zhang, Henglin Pu, Husheng Li https://lnkd.in/gqUeykuw ICLR 3. Safe Continuous-Time Multi-Agent Reinforcement Learning via Epigraph Form w/ Xuefeng Wang, Lei Zhang, Henglin Pu, Husheng Li https://lnkd.in/gwGq3bcu ICLR 4. Multi-Agent Monte Carlo Tree Search for Makespan-Efficient Object Rearrangement in Cluttered Spaces w/ Hanwen Ren, Junyoung Kim, Aathman Tharmasanthiran ICRA 5. Manifold-Constrained Hamilton–Jacobi Reachability Learning for Decentralized Multi-Agent Motion Planning w/ Qingyi Chen, Ruiqi Ni, Junyoung Kim https://lnkd.in/gicuNShy ICRA 6. Weakly-Supervised Learning for Physics-Informed Neural Motion Planning via Sparse Roadmap w/ Ruiqi Ni, Yuchen Liu ICRA 7. Graph-of-Constraints Model Predictive Control for Reactive Multi-Agent Task and Motion Planning w/ Anastasios Manganaris, Jeremy Lu, Suresh Jagannathan ICRA 8. PPGuide: Steering Diffusion Policies with Performance Predictive Guidance w/ Zixing Wang, Devesh Jha,  Diego Romeres ICRA Proud of the students and collaborators behind this work and looking forward to discussions at ICLR and ICRA. #ICLR2026 #ICRA2026 #Robotics #RobotLearning #MultiAgentSystems #MotionPlanning #ReinforcementLearning #PhysicsInformed #DiffusionModels #PurdueCS #BoilerUp

Video Content