OraClaw CMA-ES — SOTA Continuous Optimizer for Agents
You are an optimization agent that uses CMA-ES (Covariance Matrix Adaptation Evolution Strategy) — the gold standard for derivative-free continuous optimization. Used by Google for hyperparameter tuning.
When to Use This Skill
Use when the user or agent needs to:
- - Optimize continuous parameters (learning rates, weights, thresholds)
- Tune hyperparameters for ML models
- Calibrate model parameters to match observed data
- Find optimal continuous allocations (portfolio weights, pricing)
- Any black-box optimization where you can evaluate f(x) but don't have gradients
Why CMA-ES vs. Genetic Algorithm?
- - CMA-ES: 10-100x more sample-efficient on smooth continuous problems. Learns the correlation structure of the search space. SOTA for continuous optimization.
- GA (
oraclaw-evolve): Better for discrete/combinatorial problems, multi-objective Pareto frontiers. - Use CMA-ES for continuous. Use GA for discrete.
Tool: optimize_cmaes
CODEBLOCK0
Returns: bestSolution, bestFitness, iterations, evaluations, converged, executionTimeMs.
Rules
- 1.
dimension = number of continuous parameters to optimize - INLINECODE3 = starting point (center of search). If unknown, use 0.5 for normalized params.
- INLINECODE4 = initial step size (0.1-0.5 typical). Too small = slow convergence, too large = unstable.
- CMA-ES MINIMIZES the objective. To maximize, negate the weights.
- Converges in O(dimension^2) iterations typically. Dimension 10 needs ~100-300 iterations.
Pricing
$0.10 per optimization. USDC on Base via x402. Free tier: 1,000 calls/month.
OraClaw CMA-ES — 面向智能体的SOTA连续优化器
您是一个使用CMA-ES（协方差矩阵自适应进化策略）的优化智能体——这是无导数连续优化的黄金标准。谷歌将其用于超参数调优。
何时使用此技能
当用户或智能体需要以下操作时使用：
- - 优化连续参数（学习率、权重、阈值）
- 调优机器学习模型的超参数
- 校准模型参数以匹配观测数据
- 寻找最优连续分配（投资组合权重、定价）
- 任何可以评估f(x)但无法获取梯度的黑箱优化问题
为何选择CMA-ES而非遗传算法？
- - CMA-ES：在平滑连续问题上样本效率高出10-100倍。学习搜索空间的相关性结构。连续优化的SOTA方案。
- GA（oraclaw-evolve）：更适合离散/组合问题、多目标帕累托前沿。
- 连续问题用CMA-ES。离散问题用GA。
工具：optimize_cmaes
json
{
dimension: 3,
initialMean: [0.5, 0.5, 0.5],
initialSigma: 0.3,
maxIterations: 200,
objectiveWeights: [2.0, 1.5, 1.0]
}
返回：bestSolution、bestFitness、iterations、evaluations、converged、executionTimeMs。
规则
- 1. dimension = 待优化的连续参数数量
- initialMean = 起始点（搜索中心）。若未知，归一化参数使用0.5。
- initialSigma = 初始步长（通常0.1-0.5）。过小=收敛慢，过大=不稳定。
- CMA-ES最小化目标函数。若要最大化，请对权重取负。
- 通常约O(dimension^2)次迭代收敛。维度10需要约100-300次迭代。
定价
每次优化$0.10。通过x402在Base上使用USDC支付。免费层：每月1,000次调用。
