liqiang/ai-agent-book
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

ai-agent-book 精选快照（<2MB 代码与文档，来自 github.com/bojieli/ai-agent-book）
Build latest book artifacts / build (push) Canceled after 0s
Details
dependency resolution / resolve (3.11) (push) Canceled after 0s
Details
dependency resolution / resolve (3.13) (push) Canceled after 0s
Details
deploy-pages / build (push) Canceled after 0s
Details
deploy-pages / deploy (push) Canceled after 0s
Details
i18n consistency check / check (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
Details
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
Details
web-search-agent tests / test (push) Canceled after 0s
Details
web-search-agent tests / agentbook (push) Canceled after 0s
Details

Browse Source
This commit is contained in:
liqiang
2026-08-20 13:12:50 +00:00
commit b119135836
10275 changed files with 3284984 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
book-vi/images/fig8-13.svg
+29
View File
@@ -0,0 +1,29 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 40 780 450" width="780" height="450" style="background:#ffffff">
<defs><marker id="ah" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#333333" /></marker><marker id="ah-light" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#999999" /></marker></defs>
<rect x="40" y="80" width="160" height="50" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2" />
<text x="120" y="105" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Nhập Prompt x</text>
<line x1="202" y1="105" x2="238" y2="105" stroke="#333333" stroke-width="2" marker-end="url(#ah)" />
<rect x="240" y="50" width="280" height="120" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2" />
<text x="380" y="0" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold"><tspan x="380" dy="101.36">Mô hình chính sách πθ lấy mẫu</tspan><tspan x="380" dy="17.28">song song</tspan></text>
<text x="255" y="90.56" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">y₁: (8+6)×3-4 = 38 ✗</text>
<text x="255" y="103.52" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">y₂: 3×4×(8-6) = 24 ✓</text>
<text x="255" y="116.48" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">y₃: 8×4-6-3 = 23 ✗</text>
<text x="255" y="129.44" font-family="'Courier New', Courier, monospace" font-size="12" fill="#333333" text-anchor="start" dominant-baseline="central">y₄: (8+4)×3÷6 = 6 ✗</text>
<line x1="522" y1="105" x2="558" y2="105" stroke="#333333" stroke-width="2" marker-end="url(#ah)" />
<rect x="560" y="70" width="190" height="98" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2" />
<text x="655" y="0" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14.81" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold"><tspan x="655" dy="83.01">Tính toán phần</tspan><tspan x="655" dy="15.99">thưởng</tspan></text>
<text x="655" y="114" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12.96" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">R₁ = 0 (lỗi)</text>
<text x="655" y="128" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12.96" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">R₂ = 1 (đúng)</text>
<text x="655" y="141.99" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12.96" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">R₃ = 0 (lỗi)</text>
<text x="655" y="155.99" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12.96" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">R₄ = 0 (lỗi)</text>
<rect x="40" y="220" width="700" height="70" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2" />
<text x="390" y="238" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Tính toán lợi thế so sánh (không cần mạng giá trị)</text>
<text x="390" y="262" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">A(yi) = (Ri - mean(R)) / std(R) → A1=-0.58 A2=+1.73 A3=-0.58 A4=-0.58</text>
<rect x="40" y="315" width="700" height="100" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2" />
<text x="390" y="341.24" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Cập nhật chính sách (cắt tỉa đối xứng)</text>
<text x="390" y="360.68" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">L = -E[ min(r(θ)·A, clip(r(θ), 1-ε, 1+ε)·A) ]</text>
<text x="390" y="0" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal"><tspan x="390" dy="376.88">Phạm vi cắt đối xứng [1-ε, 1+ε], ε=0.2 · Ưu điểm đến từ sự so sánh tương đối trong nhóm mà</tspan><tspan x="390" dy="15.12">không cần mạng giá trị</tspan></text>
<text x="390" y="435" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Ưu điểm cốt lõi của GRPO</text>
<text x="390" y="460" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal"><tspan x="390" dy="-8.26">Không cần mô hình phần thưởng/mạng giá trị · So sánh tương đối trong các nhóm · Duy trì khả năng khám</tspan><tspan x="390" dy="16.52">phá trực tuyến · Thích hợp cho các kịch bản phần thưởng có thể kiểm chứng</tspan></text>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 6.0 KiB