Learning Sim-to-Real Humanoid Locomotion in 15 Minutes
younggyo.me · 354 words · saved by 1 readers
Learning Sim-to-Real Humanoid Locomotion in 15 Minutes
Amazon FAR (Frontier AI & Robotics) * Equal contribution We provide a simple recipe with FastSAC and FastTD3 for rapid sim-to-real humanoid iterations Abstract Massively parallel simulation has reduced reinforcement learning (RL) training time for robots from days to minutes. However, achieving fast and reliable sim-to-real RL for humanoid control remains difficult due to the challenges introduced by factors such as high dimensionality and domain randomization. In this work, we introduce a simple and practical recipe based on off-policy RL algorithms, i.e., FastSAC and FastTD3, that…
saved by
related reading
- Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningarxiv.org
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusiondiffusion-policy.cs.columbia.edu
- State of Robot Learning, December 2025vedder.io
- A Unified Model for Motion-Conditioned Robot Co-designtransformer-transformer.github.io
- Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learningarxiv.org
- BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusionarxiv.org
- [2603.08546] Interactive World Simulator for Robot Policy Training and Evaluationarxiv.org
- Generating Robot Hands from Human Demonstrationsarxiv.org
- Scalable Behavior Cloning with Open Data, Training, and Evaluationabc.bot
- [2103.06326] S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learningarxiv.org
- Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Trainingalphaxiv.org
- [2607.15275] RoboTTT: Context Scaling for Robot Policiesarxiv.org