Reinforcement learning (RL) has driven significant progress in robotics, but its complexity and long training times remain major bottlenecks. In this report, we introduce FastTD3, a simple, fast, and capable RL algorithm that significantly speeds up training for humanoid robots in popular suites such as HumanoidBench, IsaacLab, and MuJoCo Playground. Our recipe is remarkably simple: we train an off-policy TD3 agent with several modifications -- parallel simulation, large-batch updates, a distributional critic, and carefully tuned hyperparameters. FastTD3 solves a range of HumanoidBench tasks in under 3 hours on a single A100 GPU, while remaining stable during training. We also provide a lightweight and easy-to-use implementation of FastTD3 to accelerate RL research in robotics.
View on arXiv@article{seo2025_2505.22642,
title={ FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control },
author={ Younggyo Seo and Carmelo Sferrazza and Haoran Geng and Michal Nauman and Zhao-Heng Yin and Pieter Abbeel },
journal={arXiv preprint arXiv:2505.22642},
year={ 2025 }
}