Module algorithms 

Concrete evolutionary algorithms.

Classical families

• ga / ga_binary — Genetic Algorithm (real- and binary-coded).
• es_classical — (1+1), (1+λ), (μ,λ), (μ+λ) Evolution Strategies.
• cma_es — Covariance Matrix Adaptation ES (CSA + evolution paths + rank-1/rank-μ covariance updates).
• cmsa_es — Covariance Matrix Self-Adaptation ES (path-free; per-individual log-normal σ + rank-μ ML covariance blend).
• de — Differential Evolution (rand/best/current-to-best × bin/exp).
• ep — Evolutionary Programming (Fogel-style).
• gp_cgp — Cartesian Genetic Programming.
• gep — Gene Expression Programming (linear head/tail genome decoded to an expression tree).

Swarm / nature-inspired metaheuristics

• metaheuristic — PSO, ACO_R, ABC, GWO, WOA, CS, FA, BA, SSA.

Estimation-of-distribution algorithms

• eda — EdaStrategy over a ProbabilityModel: UMDA, PBIL, compact-GA, and a dependency-chain MIMIC model.

Hybrid / composite strategies

• memetic — MemeticWrapper: wraps any real-valued strategy with per-individual local-search refinement (Lamarckian / Baldwinian / Partial writeback).
• neuroevolution — WeightOnly: wraps any real-valued strategy to evolve the flattened weights of a Burn Module.

Modules

cma_es

Covariance Matrix Adaptation Evolution Strategy (CMA-ES).

cmsa_es

Covariance Matrix Self-Adaptation Evolution Strategy (CMSA-ES).

de

Differential Evolution.

eda

Estimation-of-distribution algorithms (EDAs).

ep

Evolutionary Programming (Fogel-style).

es_classical

Classical Evolution Strategies.

ga

Real-valued Genetic Algorithm.

ga_binary

Binary-coded Genetic Algorithm.

gep

Gene Expression Programming (GEP).

gp_cgp

Cartesian Genetic Programming.

memetic

Memetic-algorithm strategy adapter.

metaheuristic

Swarm-intelligence and nature-inspired metaheuristics.

neuroevolution

Neuroevolution strategies — evolving the parameters of a Burn Module.