Residual Off-Policy RL for Finetuning Behavior Cloning Policies
Paper • 2509.19301 • Published • 20
Lars Lien Ankile PRO
ankile
AI & ML interests
RL and robotics
Recent Activity
updated a dataset about 2 hours ago
ankile/real01b-marker-d2-r2-fixedinit-checkpoint100000-heldout-sobol50 published a dataset about 2 hours ago
ankile/real01b-marker-d2-r2-fixedinit-checkpoint100000-heldout-sobol50 updated a dataset about 22 hours ago
ankile/real01b-square-d2-ours-sobol-r2-ef25cov25-freecfOrganizations
authored a
paper 6 months ago