JaeHyeok Doo

jaehyeokdoo2

4

·

https://www.linkedin.com/in/jaehyeok-doo-5768a5231/

AI & ML interests

Reinforcement Learning

Recent Activity

authored a paper 1 day ago

Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy

upvoted a paper 5 days ago

Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy

updated a model 3 months ago

jaehyeokdoo2/droid-stack-three-blocks-qflow-warmup2000-offline2000-alpha10-q_aggmean-bs32-e2000

View all activity

Organizations

jaehyeokdoo2 's models 38

jaehyeokdoo2/droid-stack-three-blocks-qflow-warmup2000-offline2000-alpha10-q_aggmean-bs32-e2000

jaehyeokdoo2/pi05_droid_finetune-stack-three-blocks-steps1500

Robotics • 4B • Updated Apr 9

jaehyeokdoo2/pi05_droid_finetune-cube-stacking-order-steps1500

Robotics • 4B • Updated Apr 7

jaehyeokdoo2/pi05_droid_finetune-cube-stacking-order-qflow-lambda10-q_aggmean-bs32-steps6000

Robotics • 4B • Updated Apr 5

jaehyeokdoo2/pi05_droid_finetune-cube-stacking-order-steps10000

Robotics • 4B • Updated Apr 4

jaehyeokdoo2/pi05_droid_finetune-cube-stacking-order-steps4000

Robotics • 4B • Updated Apr 4

jaehyeokdoo2/droid-cube-stacking-qflow-criticwarmup2000-alpha1-q_aggmean-bs32-e3000

jaehyeokdoo2/droid-cube-stacking-qflow-criticwarmup2000-alpha3-q_aggmean-bs32-e3000

jaehyeokdoo2/droid-cube-stacking-qflow-criticwarmup3000-alpha10-q_aggmean-bs32-e3000

jaehyeokdoo2/droid-cube-stacking-finetune-e20000

Robotics • 4B • Updated Mar 10

jaehyeokdoo2/droid-cube-stacking-qflow-criticwarmup3000-alpha10-q_aggmean-bs32-test-e5000

jaehyeokdoo2/droid-cube-stacking-finetune-e5000

Robotics • 4B • Updated Mar 9

jaehyeokdoo2/droid-pnp-cubes2plates-finetune-e5000

Robotics • 4B • Updated Mar 9

jaehyeokdoo2/droid-pnp-cubes2plates-qflow-criticwarmup3000-alpha10-q_aggmean-bs32-test-e5000

jaehyeokdoo2/droid-object-stacking-prelim-qflow-criticwarmup3000-alpha5-q_aggmean-bs32-test-e5000

jaehyeokdoo2/droid-object-stacking-prelim-qflow-criticwarmup3000-alpha10-q_aggmean-bs32-test-e5000

jaehyeokdoo2/droid-object-stacking-prelim-qflow-cw5000-offline20000-alpha100-q_aggmean-bs32-test-e20000

Robotics • 4B • Updated Mar 7

jaehyeokdoo2/droid-object-stacking-prelim-qflow-cw5000-offline20000-alpha30-q_aggmean-bs32-test-e20000

Robotics • 4B • Updated Mar 7

jaehyeokdoo2/droid-object-stacking-prelim-qflow-criticwarmup3000-alpha50-q_aggmin-bs32-test-e5000

jaehyeokdoo2/droid-finetune-object-stacking-prelim-e3000

Robotics • 4B • Updated Mar 6

jaehyeokdoo2/openpi-droid-pnpcarrot-singetask-qflow-offlinerl-criticwarmup2000-alpha10-bs8-test

jaehyeokdoo2/openpi-droid-pnpcarrot-singetask-qflow-offlinerl-criticwarmup2000-alpha50-bs8-test

jaehyeokdoo2/openpi-droid-pnpcarrot-singetask-qflow-offlinerl-criticwarmup2000-alpha100-bs8-test

jaehyeokdoo2/openpi-droid-finetune-object-stacking-e20000

Robotics • 4B • Updated Mar 3

jaehyeokdoo2/openpi-droid-finetune-pnpcarrot-singletask-e20000

Robotics • 4B • Updated Mar 3

jaehyeokdoo2/openpi-droid-finetune-object-stacking-e5000

Robotics • 4B • Updated Mar 2

jaehyeokdoo2/openpi-droid-finetune-pnpcarrot-singletask-e15000

Robotics • 4B • Updated Feb 25

jaehyeokdoo2/openpi-droid-finetune-pnpcarrot-singletask-e10000

Robotics • 4B • Updated Feb 25

jaehyeokdoo2/openpi-droid-finetune-pnpcarrot2orangeplate-singletask-e15000

Robotics • 4B • Updated Feb 24

jaehyeokdoo2/openpi-droid-finetune-pnpcarrot2orangeplate-singletask-e5000

Robotics • 4B • Updated Feb 23