AIGeeksGroup
/

CuriousGame

Reinforcement Learning

Model card Files Files and versions

20.4 GB

Ctrl+K

Ctrl+K

3 contributors

History: 7 commits

iwannaseeyou's picture

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

e825c97 verified 10 days ago

A_cerebellum
Add CuriousGame weights (A: Cerebellum MLP and its ablations, B: behavior-token LoRA, base Qwen3.5-9B) 24 days ago
B_behavior_token
Add CuriousGame weights (A: Cerebellum MLP and its ablations, B: behavior-token LoRA, base Qwen3.5-9B) 24 days ago
Qwen3.5-9B
Add CuriousGame weights (A: Cerebellum MLP and its ablations, B: behavior-token LoRA, base Qwen3.5-9B) 24 days ago
ablations
Add CuriousGame weights (A: Cerebellum MLP and its ablations, B: behavior-token LoRA, base Qwen3.5-9B) 24 days ago
code
Add MCU attack-task weights (policy model + attack model) and code 13 days ago
cun
Add I-CIG stage-3 RL code (Sec. 3.6) 10 days ago
main
Add MCU attack-task weights (policy model + attack model) and code 13 days ago
patches
Add inference code and MineExplorer patches 24 days ago
.gitattributes

1.58 kB
Add CuriousGame weights (A: Cerebellum MLP and its ablations, B: behavior-token LoRA, base Qwen3.5-9B) 24 days ago
README.md

23.9 kB
Add MCU attack-task weights (policy model + attack model) and code 13 days ago