sfujim/TD3
A PyTorch implementation of TD3, a deep reinforcement learning algorithm for continuous robot control.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of Twin Delayed Deep Deterministic Policy Gradients (TD3), an actor-critic reinforcement learning algorithm designed to address function approximation error. The implementation is tested on MuJoCo continuous control tasks within the OpenAI gym environment. It includes both the TD3 algorithm and a DDPG implementation for comparative purposes, with networks trained on PyTorch and support for configurable hyperparameters.
Frequently asked
- What is sfujim/TD3?
- A PyTorch implementation of TD3, a deep reinforcement learning algorithm for continuous robot control.
- Is TD3 open source?
- Yes — sfujim/TD3 is open source, released under the MIT license.
- What language is TD3 written in?
- sfujim/TD3 is primarily written in Python.
- How popular is TD3?
- sfujim/TD3 has 2.1k stars on GitHub.
- Where can I find TD3?
- sfujim/TD3 is on GitHub at https://github.com/sfujim/TD3.