SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Paper • 2506.24119 • Published • 51 •
6
Zhenghao Chi
Felix-Zhenghao
AI & ML interests
None yet
Recent Activity
commentedon a paper 7 days ago
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via
Multi-Agent Multi-Turn Reinforcement Learning liked a dataset 24 days ago
allenai/dolma3_mix-6T upvoted an article about 1 month ago
Keep the Tokens Flowing: Lessons from 16 Open-Source RL LibrariesOrganizations
commented a
paper 7 days ago
Decode ground truth token but get 25% success rate on libero-10
3
#15 opened about 1 year ago
by Felix-Zhenghao
Decode ground truth token but get 25% success rate on libero-10
3
#15 opened about 1 year ago
by Felix-Zhenghao
Decode ground truth token but get 25% success rate on libero-10
3
#15 opened about 1 year ago
by Felix-Zhenghao