MultiRL

non-profit

AI & ML interests

None defined yet.

Recent Activity

KimSHine updated a model 2 days ago

MultiRL/qwen3_4b_sudoku_one_act_sft_final

KimSHine published a model 2 days ago

MultiRL/qwen3_4b_sudoku_one_act_sft_final

KimSHine updated a model 6 days ago

MultiRL/qwen3_1.7b_sudoku_multi_action_one_act_allow_21_30_epoch2

View all activity

MultiRL 's datasets 68

MultiRL/last_final_sudoku_hard_benchmark_no_hardskill

Viewer • Updated 6 days ago • 174 • 11

MultiRL/last_final_sudoku_benchmark_all

Viewer • Updated 9 days ago • 987 • 26

MultiRL/sudoku_benchmark_variants

Viewer • Updated 9 days ago • 87 • 25

MultiRL/last_final_sudoku_hard_benchmark

Viewer • Updated 9 days ago • 250 • 93

MultiRL/last_final_sudoku_standard_benchmark_hotfix

Viewer • Updated 9 days ago • 650 • 39

MultiRL/last_final_sudoku_standard_benchmark_hotfix_only

Viewer • Updated 9 days ago • 100 • 32

MultiRL/final_one_action_sudoku_sft_C

Viewer • Updated 11 days ago • 1.15k • 18

MultiRL/final_one_action_sudoku_sft_B

Viewer • Updated 11 days ago • 766 • 9

MultiRL/final_one_action_sudoku_sft_A

Viewer • Updated 11 days ago • 383 • 4

MultiRL/last_final_rush_hour_benchmark_600

Viewer • Updated 11 days ago • 600 • 55

MultiRL/rush_hour_benchmark_200_19_21

Viewer • Updated 12 days ago • 200 • 9

MultiRL/rush_hour_benchmark_320_13_21

Viewer • Updated 12 days ago • 320 • 21

MultiRL/rush_hour_sft_multi_move_final

Viewer • Updated 12 days ago • 318 • 14

MultiRL/last_final_sudoku_standard_benchmark

Viewer • Updated 12 days ago • 550 • 56

MultiRL/rush_hour_benchmark_900_4_12

Viewer • Updated 12 days ago • 900 • 22

MultiRL/rush_hour_sft_one_move_final

Viewer • Updated 12 days ago • 318 • 19

MultiRL/rush_hour_rl_10_12

Viewer • Updated 13 days ago • 640 • 20

MultiRL/rush_hour_rl_7_9

Viewer • Updated 13 days ago • 640 • 16

MultiRL/rush_hour_rl_4_6

Viewer • Updated 13 days ago • 640 • 18

MultiRL/rush_hour_benchmark_320_minmove_12_15

Viewer • Updated 13 days ago • 320 • 17

MultiRL/new_sudoku_benchmark_2045_with_variants_extra_only

Viewer • Updated 13 days ago • 1k • 26

MultiRL/new_sudoku_benchmark_2045_with_variants

Viewer • Updated 13 days ago • 2.13k • 23

MultiRL/new_v2_sudoku_easy_long_rl_21_30

Viewer • Updated 14 days ago • 640 • 52

MultiRL/new_v2_sudoku_easy_mid_rl_11_20

Viewer • Updated 14 days ago • 640 • 44

MultiRL/new_v2_sudoku_easy_short_rl_5_10

Viewer • Updated 14 days ago • 640 • 40

MultiRL/rush_hour_benchmark_570_minmove_3_30

Viewer • Updated 14 days ago • 570 • 33

MultiRL/final_one_action_sudoku_sft_filtered_new

Viewer • Updated 15 days ago • 540 • 34

MultiRL/new_sudoku_easy_long_rl

Viewer • Updated 16 days ago • 640 • 32

MultiRL/new_sudoku_easy_short_rl

Viewer • Updated 16 days ago • 640 • 42

MultiRL/final_one_action_sudoku_sft_filtered

Viewer • Updated 16 days ago • 540 • 17