FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control
This addresses training bottlenecks for robotics researchers, though it appears incremental as it builds on existing TD3 methods.
The paper tackled the problem of slow and complex reinforcement learning for humanoid robots by introducing FastTD3, which solves HumanoidBench tasks in under 3 hours on a single A100 GPU.
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.