ikostrikov/pytorch-trpo

PyTorch implementation of Trust Region Policy Optimization

50
/ 100
Established

This project helps machine learning researchers implement the Trust Region Policy Optimization (TRPO) algorithm for training AI agents. You provide a simulation environment, and it outputs a learned policy that enables an agent to perform tasks within that environment. This is for researchers and practitioners in reinforcement learning who need to experiment with or apply this specific policy optimization method.

450 stars. No commits in the last 6 months.

Use this if you are a reinforcement learning researcher specifically interested in implementing or evaluating the Trust Region Policy Optimization (TRPO) algorithm using PyTorch.

Not ideal if you are looking for the latest, state-of-the-art policy optimization method, as a newer variant (PPO) is generally recommended instead.

reinforcement-learning AI-agent-training policy-optimization robotics-simulation machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

450

Forks

91

Language

Python

License

MIT

Last pushed

Sep 13, 2018

Commits (30d)

0

Get this data via API

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

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