ikostrikov/pytorch-a3c

PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".

51
/ 100
Established

This project helps machine learning researchers implement and experiment with the Asynchronous Advantage Actor Critic (A3C) algorithm for reinforcement learning. It takes in environment specifications and training parameters, and outputs a trained agent capable of learning complex tasks like playing games. This is used by researchers focused on developing and evaluating reinforcement learning agents.

1,317 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher specifically interested in implementing and studying the A3C algorithm for deep reinforcement learning problems.

Not ideal if you are looking for the most performant or cutting-edge reinforcement learning algorithm, as A2C, PPO, or ACKTR might offer better results and are recommended by the author.

reinforcement-learning deep-learning algorithm-research agent-training AI-experimentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,317

Forks

281

Language

Python

License

MIT

Last pushed

Sep 25, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ikostrikov/pytorch-a3c"

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