awesome-repositories.com
Blog
MCP
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetÀ proposNotre méthodologiePresseServeur MCP
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
ikostrikov avatar

ikostrikov/pytorch-a2c-ppo-acktr-gail

0
View on GitHub↗
3,901 stars·843 forks·Python·MIT·8 vues

Pytorch A2c Ppo Acktr Gail

Il s'agit d'une bibliothèque d'apprentissage par renforcement PyTorch conçue pour entraîner des agents dans des environnements de simulation. Elle fournit une collection d'algorithmes d'apprentissage par renforcement profond se concentrant sur les méthodes de gradient de politique et l'optimisation de région de confiance (trust-region).

La bibliothèque implémente une suite d'algorithmes de gradient de politique, incluant A2C et PPO, ainsi qu'un framework pour l'apprentissage par imitation utilisant Generative Adversarial Imitation Learning. Elle propose spécifiquement une implémentation évolutive de l'algorithme ACKTR, utilisant des approximations factorisées de Kronecker pour permettre une optimisation efficace de la région de confiance.

La base de code couvre des capacités plus larges, notamment des interfaces d'environnement standardisées pour l'intégration de simulation, le traitement par lots basé sur l'expérience et des outils pour visualiser le comportement des agents et la progression de l'entraînement.

Features

  • Reinforcement Learning Training - Provides a comprehensive framework for training deep reinforcement learning agents in simulation environments using PyTorch.
  • Actor-Critic Architectures - Utilizes actor-critic architectures with separate networks for action probabilities and state value estimation.
  • Kronecker-Factored Trust Region Methods - Implements Kronecker-factored approximations to scale trust-region optimization for large neural networks with lower compute costs.
  • Policy Gradient Methods - Ships a suite of policy gradient algorithms, including A2C and PPO, for optimizing agent behavior.
  • Proximal Policy Optimization - Provides advanced policy optimization through methods such as Proximal Policy Optimization and trust-region updates.
  • PyTorch Reinforcement Learning Libraries - Offers a collection of standard deep reinforcement learning algorithms implemented in PyTorch for simulation environments.
  • Trust Region Policy Optimization - Supports scaled trust-region policy optimization using Kronecker-factored approximations for stable and efficient updates.
  • Simulation Training Environments - Integrates deep learning models with physics engines and game simulators for behavioral training and testing.
  • Adversarial Imitation - Enables agents to mimic expert behavior using generative adversarial imitation learning frameworks.
  • Clipped Policy Objectives - Implements clipped surrogate objectives within PPO to maintain training stability and prevent catastrophic performance drops.
  • Environment Wrappers - Offers a standardized API wrapper to decouple reinforcement learning agent logic from various simulation engine physics.
  • Simulation Environment Interfacing - Implements a standardized interface for connecting agents to simulated environments for action-reward based learning.

Historique des stars

Graphique de l'historique des stars pour ikostrikov/pytorch-a2c-ppo-acktr-gailGraphique de l'historique des stars pour ikostrikov/pytorch-a2c-ppo-acktr-gail

Recherche par IA

Explorez plus de dépôts awesome

Décrivez vos besoins en langage naturel — l'IA classe des milliers de projets open source sélectionnés par pertinence.

Start searching with AI

Questions fréquentes

Que fait ikostrikov/pytorch-a2c-ppo-acktr-gail ?

Il s'agit d'une bibliothèque d'apprentissage par renforcement PyTorch conçue pour entraîner des agents dans des environnements de simulation. Elle fournit une collection d'algorithmes d'apprentissage par renforcement profond se concentrant sur les méthodes de gradient de politique et l'optimisation de région de confiance (trust-region).

Quelles sont les fonctionnalités principales de ikostrikov/pytorch-a2c-ppo-acktr-gail ?

Les fonctionnalités principales de ikostrikov/pytorch-a2c-ppo-acktr-gail sont : Reinforcement Learning Training, Actor-Critic Architectures, Kronecker-Factored Trust Region Methods, Policy Gradient Methods, Proximal Policy Optimization, PyTorch Reinforcement Learning Libraries, Trust Region Policy Optimization, Simulation Training Environments.

Quelles sont les alternatives open-source à ikostrikov/pytorch-a2c-ppo-acktr-gail ?

Les alternatives open-source à ikostrikov/pytorch-a2c-ppo-acktr-gail incluent : openai/baselines — Baselines is a comprehensive suite of frameworks for reinforcement learning algorithm implementation, imitation… p-christ/deep-reinforcement-learning-algorithms-with-pytorch — This is a PyTorch-based toolkit for training reinforcement learning agents, providing implementations of standard and… andri27-ts/reinforcement-learning — This project is a collection of reinforcement learning implementations and educational materials written in Python. It… facebookresearch/horizon — Horizon is a reinforcement learning platform designed for training, evaluating, and deploying agents and contextual… lazyprogrammer/machine_learning_examples — This project is a comprehensive collection of practical code examples and implementation libraries for machine… morvanzhou/tutorials — This repository is a comprehensive collection of instructional guides and practical examples for Python development,…

Alternatives open source à Pytorch A2c Ppo Acktr Gail

Projets open source similaires, classés selon le nombre de fonctionnalités partagées avec Pytorch A2c Ppo Acktr Gail.
  • openai/baselinesAvatar de openai

    openai/baselines

    16,733Voir sur GitHub↗

    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

    Python
    Voir sur GitHub↗16,733
  • p-christ/deep-reinforcement-learning-algorithms-with-pytorchAvatar de p-christ

    p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch

    5,935Voir sur GitHub↗

    This is a PyTorch-based toolkit for training reinforcement learning agents, providing implementations of standard and hierarchical deep RL algorithms. It is designed as a library for deep reinforcement learning research and experimentation, supporting both discrete and continuous control tasks through a collection of algorithm implementations. The project distinguishes itself by offering a hierarchical reinforcement learning framework that decomposes complex long-horizon tasks into manageable sub-goals using meta-controllers and lower-level policies. It also includes a Hindsight Experience Re

    Python
    Voir sur GitHub↗5,935
  • andri27-ts/reinforcement-learningAvatar de andri27-ts

    andri27-ts/Reinforcement-Learning

    4,722Voir sur GitHub↗

    This project is a collection of reinforcement learning implementations and educational materials written in Python. It provides neural network architectures for solving control tasks through deep reinforcement learning, spanning value-based and policy-gradient methods. The repository includes a library of evolutionary strategies and genetic algorithms as alternatives to gradient-based learning. It also features a model-based system for predicting future environment states and rewards to enable internal simulation and offline planning. The codebase covers a wide range of capabilities, includi

    Jupyter Notebooka2cartificial-intelligencedeep-learning
    Voir sur GitHub↗4,722
  • facebookresearch/horizonAvatar de facebookresearch

    facebookresearch/Horizon

    3,703Voir sur GitHub↗

    Horizon is a reinforcement learning platform designed for training, evaluating, and deploying agents and contextual bandits using historical data. It serves as an off-policy engine and offline policy evaluation tool, allowing decision-making policies to be optimized and tested without the need for a live simulator. The framework specializes in recommendation system optimization, specifically using slating-based reinforcement learning to optimize the ordering and sequencing of multiple recommendations. It also functions as a contextual bandit framework that manages the balance between explorat

    Python
    Voir sur GitHub↗3,703
Voir les 30 alternatives à Pytorch A2c Ppo Acktr Gail→