Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Paper
•
2509.22601
•
Published
•
29
Yang Zhou
nbzy1995
·
AI & ML interests
Artificial General Intelligence, AI for Science, AI for society
Recent Activity
updated
a model
about 1 month ago
nbzy1995/Qwen2-0-5B-GRPO-vllm-trl
updated
a model
about 1 month ago
nbzy1995/Qwen2-0-5B-GRPO-vllm-trl
updated
a model
about 1 month ago
nbzy1995/Qwen2-0-5B-GRPO-vllm-trl
Organizations
upvoted
a
paper
3 months ago