https://terms-en.ai-term-hub.com/zh/tags/decision-theory/Recent content in Decision Theory on 中文AI术语词典Hugozh-cnSat, 18 Jul 2026 11:44:45 +0000https://terms-en.ai-term-hub.com/zh/terms/bayesian_regret/Sat, 18 Jul 2026 11:09:03 +0000https://terms-en.ai-term-hub.com/zh/terms/bayesian_regret/<h2 id="definition">Definition</h2> <p>贝叶斯遗憾量化了在拥有完美信息时可实现的最佳奖励与智能体在不确定性下行动所获得的预期奖励之间的差异。它是通过对所有可能的世界状态进行积分计算得出的，反映了决策者在信息不完全情况下的性能损失。</p> <h3 id="summary">Summary</h3> <p>决策理论中衡量因对世界真实状态不确定而导致的预期损失的指标。</p> <h2 id="key-concepts">Key Concepts</h2> <ul> <li>期望效用</li> <li>先验分布</li> <li>决策理论</li> <li>遗憾最小化</li> </ul> <h2 id="use-cases">Use Cases</h2> <ul> <li>强化学习评估</li> <li>多臂老虎机问题</li> <li>策略博弈分析</li> </ul> <h2 id="related-terms">Related Terms</h2> <ul> <li><a href="https://terms-en.ai-term-hub.com/en/terms/frequentist-regret-%E9%A2%91%E7%8E%87%E5%AD%A6%E6%B4%BE%E9%81%97%E6%86%BE/">Frequentist regret (频率学派遗憾)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/pareto-optimality-%E5%B8%95%E7%B4%AF%E6%89%98%E6%9C%80%E4%BC%98/">Pareto optimality (帕累托最优)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/expected-value-%E6%9C%9F%E6%9C%9B%E5%80%BC/">Expected value (期望值)</a></li> <li><a href="https://terms-en.ai-term-hub.com/en/terms/information-gain-%E4%BF%A1%E6%81%AF%E5%A2%9E%E7%9B%8A/">Information gain (信息增益)</a></li> </ul>