AutoRLBench

AI & ML interests

real-world online reinforcement learning in robotics

Recent Activity

jesbu1  authored a paper about 2 months ago

TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning

jesbu1  authored a paper about 2 months ago

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies

jesbu1  authored a paper 5 months ago

Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons

View all activity

Team members 3