AIGeeksGroup
/

CuriousGame

Reinforcement Learning

Model card Files Files and versions

Commit History

Nov 4 Yesterday

16:42
Add I-CIG stage-3 RL code (Sec. 3.6)

iwannaseeyou

Verified signature
e825c97

Nov 1 4 days ago

14:47
Add MCU attack-task weights (policy model + attack model) and code

LeoMaxwell

Verified signature
f244c2b

Oct 28 8 days ago

15:49
Add main method weights (Brain LoRA + policy model, curiosity GRPO r25)

LeoMaxwell

Verified signature
bf1c911

Oct 26 10 days ago

11:06
add cun/optimus3_train and cun/qwen_train code

iwannaseeyou

Verified signature
ffceb52

Oct 21 15 days ago

16:04
Add inference code and MineExplorer patches

LeoMaxwell

Verified signature
4764138
14:20
Add CuriousGame weights (A: Cerebellum MLP and its ablations, B: behavior-token LoRA, base Qwen3.5-9B)

LeoMaxwell

Verified signature
01bed92

Oct 19 17 days ago

08:34
initial commit

SteveZeyuZhang

Verified signature
65f788a