# FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control

arXiv: https://arxiv.org/abs/2505.22642 · HTML: https://mlsanity.com/paper/2505.22642/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 28 of its 39 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 28 of 28)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [A Distributional Perspective on Reinforcement Learning](https://mlsanity.com/paper/1707.06887/) (2017)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments](https://mlsanity.com/paper/2301.04195/) (2023)
- [Asymmetric Actor Critic for Image-Based Robot Learning](https://mlsanity.com/paper/1710.06542/) (2017)
- [MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis](https://mlsanity.com/paper/2211.09117/) (2022)
- [Emergence of Locomotion Behaviours in Rich Environments](https://mlsanity.com/paper/1707.02286/) (2017)
- [Bigger, Better, Faster: Human-level Atari with human-level efficiency](https://mlsanity.com/paper/2305.19452/) (2023)
- [HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation](https://mlsanity.com/paper/2403.10506/) (2024)
- [Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control](https://mlsanity.com/paper/2405.16158/) (2024)
- [Simplifying Deep Temporal Difference Learning](https://mlsanity.com/paper/2407.04811/) (2024)
- [MuJoCo Playground](https://mlsanity.com/paper/2502.08844/) (2025)
- [SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning](https://mlsanity.com/paper/2410.09754/) (2024)
- [Normalization and effective learning rates in reinforcement learning](https://mlsanity.com/paper/2407.01800/) (2024)
- [Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning](https://mlsanity.com/paper/2403.00514/) (2024)
- [Towards General-Purpose Model-Free Reinforcement Learning](https://mlsanity.com/paper/2501.16142/) (2025)
- [BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark](https://mlsanity.com/paper/2407.07788/) (2024)
- [MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL](https://mlsanity.com/paper/2410.08896/) (2024)
- [TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control](https://mlsanity.com/paper/2502.17322/) (2025)

## Built on by (most cited first, 30 of 44)

- [floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL](https://mlsanity.com/paper/2509.06863/) (2025)
- [Learning Sim-to-Real Humanoid Locomotion in 15 Minutes](https://mlsanity.com/paper/2512.01996/) (2025)
- [Flow Policy Gradients for Robot Control](https://mlsanity.com/paper/2602.02481/) (2026)
- [DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion](https://mlsanity.com/paper/2509.14353/) (2025)
- [Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents](https://mlsanity.com/paper/2510.13704/) (2025)
- [Learning Massively Multitask World Models for Continuous Control](https://mlsanity.com/paper/2511.19584/) (2025)
- [Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning](https://mlsanity.com/paper/2511.07730/) (2025)
- [Relative Entropy Pathwise Policy Optimization](https://mlsanity.com/paper/2507.11019/) (2025)
- [FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control](https://mlsanity.com/paper/2604.04539/) (2026)
- [Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints](https://mlsanity.com/paper/2510.08549/) (2025)
- [OMP: One-step Meanflow Policy with Directional Alignment](https://mlsanity.com/paper/2512.19347/) (2025)
- [What Makes Value Learning Efficient in Residual Reinforcement Learning?](https://mlsanity.com/paper/2602.10539/) (2026)
- [AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learning](https://mlsanity.com/paper/2603.20147/) (2026)
- [Combined Constrained Sampling and Reinforcement Learning for Robotic Manipulation](https://mlsanity.com/paper/2602.08557/) (2026)
- [What Matters for Simulation to Online Reinforcement Learning on Real Robots](https://mlsanity.com/paper/2602.20220/) (2026)
- [Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL](https://mlsanity.com/paper/2511.11592/) (2025)
- [Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics](https://mlsanity.com/paper/2602.21203/) (2026)
- [Trust-Region Diffusion Policies for Massively Parallel On-Policy RL](https://mlsanity.com/paper/2606.15260/) (2026)
- [Scaling Behavior Foundation Model for Humanoid Robots](https://mlsanity.com/paper/2607.15163/) (2026)
- [Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies](https://mlsanity.com/paper/2508.03194/) (2025)
- [Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control](https://mlsanity.com/paper/2601.21363/) (2026)
- [Reward-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2603.05066/) (2026)
- [NFPO: Stabilized Policy Optimization of Normalizing Flow for Robotic Policy Learning](https://mlsanity.com/paper/2603.11470/) (2026)
- [FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control](https://mlsanity.com/paper/2603.12612/) (2026)
- [ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors](https://mlsanity.com/paper/2603.15956/) (2026)
- [Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning](https://mlsanity.com/paper/2603.25464/) (2026)
- [Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty](https://mlsanity.com/paper/2604.25508/) (2026)
- [Debiased Model-based Representations for Sample-efficient Continuous Control](https://mlsanity.com/paper/2605.11711/) (2026)
- [AnyBody: Free-Form Whole-Body Humanoid Control from Arbitrary Keypoint Guidance](https://mlsanity.com/paper/2606.29209/) (2026)
- [Functional Critics Are Essential for Actor-Critic: From Off-Policy Stability to Efficient Exploration](https://mlsanity.com/paper/2509.22964/) (2025)

## Abstract (arXiv)

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.