Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy Paper • 2605.13435 • Published 13 days ago • 1
jdoo2/droid-stack-three-blocks-qflow-warmup2000-offline2000-alpha10-q_aggmean-bs32-e2000 Updated Apr 10
jdoo2/droid-stack-three-blocks-qflow-warmup2000-offline2000-alpha10-q_aggmean-bs32-e2000 Updated Apr 10
jdoo2/pi05_droid_finetune-cube-stacking-order-qflow-lambda10-q_aggmean-bs32-steps6000 Robotics • 4B • Updated Apr 5
jdoo2/pi05_droid_finetune-cube-stacking-order-qflow-lambda10-q_aggmean-bs32-steps6000 Robotics • 4B • Updated Apr 5