Unverified50% confidenceFactExact time
Shapley值从合作博弈论出发通过计算边际贡献期望分配信用，但计算复杂度随智能体数量指数增长
1
Sources
50%
Confidence
Long-term
Relevance
8/7/2026
First Seen
Sources
M.A.R.A：用强化学习从零训练会战斗的AI坦克
Related Claims
UnverifiedIn multi-agent team cooperation, there exists a credit assignment problem, namely how to determine each member's contribution when the team wins.69% similarUnverified推理能力越强的模型生成内容越详尽，单次交互token消耗随之攀升，形成「能力越强、消耗越大」的技术约束64% similarUnverifiedThe higher the reasoning effort level, the stronger the reasoning capability but the faster token consumption, representing a trade-off between cost and intelligence.62% similarUnverified从个人贡献者到乘数型角色的跃迁，衡量价值的标准从个人技术能力转变为让团队相信问题能够被解决61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/699558API
curl https://kongchang.com/api/v1/knowledge/claims/699558MCP
get_claim(id=699558)