10 repositorios
Libraries and collections providing ready-to-use reinforcement learning algorithms.
Explore 10 awesome GitHub repositories matching part of an awesome list · Algorithm Implementations. Refine with filters or upvote what's useful.
Baselines is a comprehensive suite of frameworks for reinforcement learning algorithm implementation, imitation learning, and training orchestration. It provides a library of standardized learning algorithms used to benchmark and replicate research results, alongside a deep learning policy framework for constructing neural network architectures such as multi-layer perceptrons, convolutional networks, and long short-term memory networks. The project includes a specialized imitation learning toolkit that enables agents to mimic expert behavior through behavior cloning and generative adversarial
Well-tested implementations of standard reinforcement learning algorithms.
MLAlgorithms es una biblioteca educativa de algoritmos de machine learning que consiste en modelos predictivos principales implementados desde cero en Python. Sirve como referencia para que los desarrolladores estudien la lógica interna y el funcionamiento matemático de estos modelos a través de implementaciones limpias y minimalistas. El código base se centra en el estudio de la implementación de algoritmos y la educación en machine learning, proporcionando una forma de entender la mecánica interna mediante la construcción de componentes sin depender de bibliotecas externas pesadas. El proyecto utiliza encapsulación orientada a objetos y vectorización basada en NumPy para gestionar el estado del modelo y realizar operaciones matemáticas. Su arquitectura enfatiza la transparencia mediante el uso de lógica en Python puro para implementar primitivas de álgebra lineal e inicialización modular de parámetros.
Implementations of common machine learning algorithms from scratch.
Minimal and Clean Reinforcement Learning Examples
Minimal and clean examples of various reinforcement learning algorithms.
Modularized Implementation of Deep RL Algorithms in PyTorch
Deep reinforcement learning algorithms implemented in PyTorch.
ChainerRL is a deep reinforcement learning library built on top of Chainer.
Deep reinforcement learning algorithms implemented in Chainer.
A deep Q learning demonstration using Google Tensorflow
Demonstration of deep Q-learning using the TensorFlow framework.
🕹️ A diverse suite of scalable reinforcement learning environments in JAX
Hardware-accelerated environments for industry-driven research.
Deep Reinforcement Learning library for humans
Library for deep reinforcement learning using Theano and Lasagne.
Persistent advantage learning dueling double DQN for the Arcade Learning Environment
Deep Q-networks and asynchronous agents implemented in Torch.
Code for the Black-DROPS algorithm: "Black-Box Data-efficient Policy Search for Robotics", IROS 2017/ICRA 2018
Modular code for model-based policy search algorithms.