liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
44 lines
8.3 KiB
XML
44 lines
8.3 KiB
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 40 780 440" width="780" height="440" 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="80" y="120" width="260" height="130" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
||
<text x="210" y="145" 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">Agent（探险者）</text>
|
||
<text x="210" y="175" 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">策略 π：观察状态 →</text>
|
||
<text x="210" y="198" 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">选择动作（移动/拾取/攻击）</text>
|
||
<text x="210" y="225" 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">ε-贪婪：90% 最优, 10% 随机</text>
|
||
<rect x="440" y="120" width="260" height="130" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="570" y="145" 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">环境（迷宫世界）</text>
|
||
<text x="570" y="175" 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">5 个房间 · 钥匙/门/守卫</text>
|
||
<text x="570" y="198" 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">转移：P(储藏室|大厅,东)=1.0</text>
|
||
<text x="570" y="225" 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">R(击败守卫)=+50, R(移动)=0</text>
|
||
<line x1="342" y1="150" x2="438" y2="150" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
||
<text x="390.0" y="136" 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">动作 A(t) = "向东移动"</text>
|
||
<line x1="438" y1="235" x2="342" y2="235" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
||
<text x="390.0" y="253" 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">状态 S(t+1) + 奖励 R(t+1)</text>
|
||
<text x="390" y="300" 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">轨迹：S(0), A(0), R(1), S(1), A(1), R(2), ...</text>
|
||
<rect x="35.0" y="340" width="134.0" height="70" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
||
<text x="102.0" y="357" 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">S(0): 入口大厅</text>
|
||
<text x="102.0" y="375" 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">A(0): 向东</text>
|
||
<text x="102.0" y="393" 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="bold">R(1): 0</text>
|
||
<line x1="171.0" y1="373" x2="181.0" y2="373" stroke="#999999" stroke-width="2" marker-end="url(#ah-light)"/>
|
||
<rect x="179.0" y="340" width="134.0" height="70" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
||
<text x="246.0" y="357" 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">S(1): 储藏室</text>
|
||
<text x="246.0" y="375" 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">A(1): 拿钥匙</text>
|
||
<text x="246.0" y="393" 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="bold">R(2): +5</text>
|
||
<line x1="315.0" y1="373" x2="325.0" y2="373" stroke="#999999" stroke-width="2" marker-end="url(#ah-light)"/>
|
||
<rect x="323.0" y="340" width="134.0" height="70" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
||
<text x="390.0" y="357" 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">S(2): 储藏室</text>
|
||
<text x="390.0" y="375" 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">A(2): 向北</text>
|
||
<text x="390.0" y="393" 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="bold">R(3): 0</text>
|
||
<line x1="459.0" y1="373" x2="469.0" y2="373" stroke="#999999" stroke-width="2" marker-end="url(#ah-light)"/>
|
||
<rect x="467.0" y="340" width="134.0" height="70" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
||
<text x="534.0" y="357" 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">S(3): 守卫室</text>
|
||
<text x="534.0" y="375" 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">A(3): 合成银剑</text>
|
||
<text x="534.0" y="393" 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="bold">R(4): +10</text>
|
||
<line x1="603.0" y1="373" x2="613.0" y2="373" stroke="#999999" stroke-width="2" marker-end="url(#ah-light)"/>
|
||
<rect x="611.0" y="340" width="134.0" height="70" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
||
<text x="678.0" y="357" 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">S(4): 守卫室</text>
|
||
<text x="678.0" y="375" 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">A(4): 攻击</text>
|
||
<text x="678.0" y="393" 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="bold">R(5): +50</text>
|
||
<text x="390" y="460" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">目标：最大化累积奖励 G = R(1) + γR(2) + γ²R(3) + ...（γ=0.99）</text>
|
||
</svg> |
