ikostrikov/pytorch-a2c-ppo-acktr-gail

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

51
/ 100
Established

This project provides pre-built solutions for training artificial intelligence to perform complex tasks, like playing Atari games or controlling robot movements. It takes a simulated environment and desired outcomes as input and generates an AI 'brain' that can make decisions to achieve those goals. Developers, researchers, and students working in machine learning and robotics would use this to experiment with different AI learning strategies.

3,879 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or developer looking to apply established reinforcement learning algorithms like A2C, PPO, ACKTR, or GAIL to simulated control tasks.

Not ideal if you need an AI that learns from continuous real-world data, as this is optimized for simulated environments, or if you prefer Soft Actor Critic (SAC) for continuous control.

reinforcement-learning robotics-simulation game-ai deep-learning-research control-systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

3,879

Forks

842

Language

Python

License

MIT

Last pushed

May 29, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ikostrikov/pytorch-a2c-ppo-acktr-gail"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.