gepa
Optimize prompts, code, and more with AI-powered Reflective Optimization
- 7.5k
- Jupyter Notebook
- MIT
- 9 d ago
Optimize prompts, code, and more with AI-powered Reflective Optimization
Infrastructure for evolutionary AI systems. GPU-accelerated, PyTorch-based optimization with an ecosystem of algorithm libraries, benchmarks, and tools.
Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.
A 2D Unity simulation in which cars learn to navigate themselves through different courses. The cars are steered by a feedforward neural network. The weights of the network are trained using a modified genetic algorithm.
The official code repository supporting the book, Grokking Artificial Intelligence Algorithms
Distributed High-Performance Symbolic Regression in Julia
Always sparse. Never dense. But never say never. A Sparse Training repository for the Adaptive Sparse Connectivity concept and its algorithmic instantiation, i.e. Sparse Evolutionary Training, to boost Deep Learning scalability on various aspects (e.g. memory and computational time efficiency, representation and generalization power).
Derivative-Free Global Optimization Algorithm (C++, Python binding) - Continuous, Discrete, TSP, NLS, MINLP
[ICML 2020] Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control
Official implementation of NeurIPS22 paper “Multi-agent Dynamic Algorithm Configuration”
reflame: Revolutionizing Functional Link Neural Network by Metaheuristic Optimization
Deterministic, task-agnostic quality-diversity evolution for .NET.