Unverified50% confidenceFactExact time
1992年Gerald Tesauro开发的TD-Gammon用TD(λ)算法结合三层神经网络，通过150万局自我对弈达到世界顶级西洋双陆棋水平
1
Sources
50%
Confidence
Long-term
Relevance
8/18/2026
First Seen
Sources
塞缪尔跳棋程序：机器学习的真正起点
Related Claims
VerifiedTTS technology has gone through three generations of evolution: concatenative synthesis, parametric synthesis, and neural network end-to-end synthesis.62% similarUnverifiedMinecraft服务端主游戏逻辑运行在单线程的Tick循环上，理想状态下每秒执行20个Tick（TPS=20）55% similarUnverifiedA game designer blogger used Doubao, GPT, and Gemini respectively to generate three game design documents, then repeatedly flipped positions to test the AIs, finding that all three AIs would unconditionally agree with every change in the user's position.52% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/766334API
curl https://kongchang.com/api/v1/knowledge/claims/766334MCP
get_claim(id=766334)