liqiang/ai-agent-book
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
main
ai-agent-book/book-ja/images/fig8-13.svg
T
liqiang b119135836
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
ai-agent-book 精选快照（<2MB 代码与文档，来自 github.com/bojieli/ai-agent-book）
2026-08-20 13:12:50 +00:00

29 lines
5.7 KiB
XML
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<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">入力プロンプト 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="70" 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">方策モデル πθ の並列サンプリング</text>
<text x="255" y="95" 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="117" 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="139" 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="161" 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="90" 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">報酬の計算</text>
<text x="655" y="112" 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">R₁ = 0（不正解）</text>
<text x="655" y="126" 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">R₂ = 1（正解）</text>
<text x="655" y="140" 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">R₃ = 0（不正解）</text>
<text x="655" y="154" 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">R₄ = 0（不正解）</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">相対アドバンテージの計算（価値ネットワーク不要）</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="337" 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">方策の更新（対称クリッピング）</text>
<text x="390" y="365" 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="390" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">対称クリッピング範囲 [1-ε, 1+ε]、ε=0.2 ・ アドバンテージはグループ内の相対比較から得られ、価値ネットワークは不要</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">GRPO の主な利点</text>
<text x="390" y="460" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">報酬モデル／価値ネットワーク不要 ・ グループ内の相対比較 ・ オンライン探索能力を維持 ・ 検証可能な報酬のシナリオに適する</text>
</svg>
Reference in New Issue View Git Blame Copy Permalink