ted88168/rollout_colorlogo_acp_r2_targeted_v1
SO-101 • Updated • 84 episodes • 115 • 1
Edit Datasets filters
Active filters: advantage-conditioned-policy
Aikwed/insert_carrot_into_the_hole_hil_success_only
SO-101 • Updated • 70 episodes • 157
ted88168/rollout_colorlogo_rl_round1
SO-101 • Updated • 120 episodes • 59
ted88168/rollout_colorlogo_stage6_eval
Viewer • Updated • 162 • 531
ted88168/rollout_colorlogo_rl_round2_combined
SO-101 • Updated • 204 episodes • 69