Checkpoints "Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning" arxiv [2509.22601]
Yulei Qin
yolay
AI & ML interests
Medical Imaging, Computer Vision,
Language Models
Recent Activity
upvoted
a
paper
about 3 hours ago
ROCKET-1: Master Open-World Interaction with Visual-Temporal Context
Prompting
updated
a model
17 days ago
yolay/SPEAR-SearchQA-Qwen2.5-14B
updated
a model
18 days ago
yolay/SPEAR-SearchQA-Qwen2.5-7B
Organizations
models
22
yolay/SPEAR-SearchQA-Qwen2.5-14B
15B
•
Updated
•
25
yolay/SPEAR-SearchQA-Qwen2.5-7B
8B
•
Updated
•
21
•
1
yolay/SPEAR-ReTool-Qwen2.5-32B
33B
•
Updated
•
27
yolay/SPEAR-ReTool-Qwen3-32B
33B
•
Updated
•
27
yolay/SPEAR-ALFWorld-DrBoT-GRPO-1.5B
2B
•
Updated
•
26
yolay/SPEAR-ALFWorld-DrBoT-GiGPO-1.5B
2B
•
Updated
•
31
yolay/SPEAR-ALFWorld-DrBoT-GRPO-7B
8B
•
Updated
•
24
yolay/SPEAR-ALFWorld-DrBoT-GiGPO-7B
8B
•
Updated
•
17
yolay/SPEAR-WebShop-DrBoT-GRPO-1.5B
2B
•
Updated
•
27
yolay/SPEAR-WebShop-DrBoT-GiGPO-1.5B
2B
•
Updated
•
100