MathMindsAGI/sokoban_qwen3_4b_instruct_tis_8k_3box_k3_kl1e-3_colocate_async_step1800 4B • Updated 1 day ago • 101
MathMindsAGI/sokoban_qwen3_4b_instruct_sc_tis_8k_3box_colocate_async_step1300 4B • Updated 1 day ago • 103
MathMindsAGI/sokoban_qwen3_4b_instruct_replay_layers_final_8k_3box_colocate_async_step1000 4B • Updated 1 day ago • 100
MathMindsAGI/sokoban_qwen3_4b_instruct_dppo_tv_8k_3box_colocate_async_step1200 4B • Updated 1 day ago • 100