# SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillation

arXiv: https://arxiv.org/abs/2407.10481 · HTML: https://mlsanity.com/paper/2407.10481/

## Key facts

- Cited by 17 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 30 of its 67 references that are in the map.
- First posted on arXiv 15 Jul 2024.

## 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, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [Language2Pose: Natural Language Grounded Pose Forecasting](https://mlsanity.com/paper/1907.01108/) (2019)
- [MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis](https://mlsanity.com/paper/2212.04495/) (2022)
- [Character Controllers Using Motion VAEs](https://mlsanity.com/paper/2103.14274/) (2021)
- [DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills](https://mlsanity.com/paper/1804.02717/) (2018)
- [MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators](https://mlsanity.com/paper/2306.10900/) (2023)
- [Neural probabilistic motor primitives for humanoid control](https://mlsanity.com/paper/1811.11711/) (2018)
- [QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars](https://mlsanity.com/paper/2209.09391/) (2022)
- [Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks](https://mlsanity.com/paper/1705.06400/) (2017)
- [ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills](https://mlsanity.com/paper/2005.04323/) (2020)
- [PADL: Language-Directed Physics-Based Character Control](https://mlsanity.com/paper/2301.13868/) (2023)
- [UniCon: Universal Neural Controller For Physics-based Character Motion](https://mlsanity.com/paper/2011.15119/) (2020)
- [Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning](https://mlsanity.com/paper/2309.11359/) (2023)
- [MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control](https://mlsanity.com/paper/2208.07363/) (2022)
- [InsActor: Instruction-driven Physics-based Characters](https://mlsanity.com/paper/2312.17135/) (2023)
- [ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characters](https://mlsanity.com/paper/2210.06063/) (2022)
- [Animating Human Athletics](https://mlsanity.com/paper/2302.06108/) (2023)
- [Learning to Manipulate Amorphous Materials](https://mlsanity.com/paper/2103.02533/) (2021)

## Built on by (most cited first, 17 of 17)

- [MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting](https://mlsanity.com/paper/2409.14393/) (2024)
- [CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control](https://mlsanity.com/paper/2410.03441/) (2024)
- [InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions](https://mlsanity.com/paper/2502.20390/) (2025)
- [UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control](https://mlsanity.com/paper/2504.12540/) (2025)
- [Reconstructing 4D Spatial Intelligence: A Survey](https://mlsanity.com/paper/2507.21045/) (2025)
- [Human-Centric Foundation Models: Perception, Generation and Agentic Modeling](https://mlsanity.com/paper/2502.08556/) (2025)
- [InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions](https://mlsanity.com/paper/2602.06035/) (2026)
- [GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill](https://mlsanity.com/paper/2504.04191/) (2025)
- [ModSkill: Physical Character Skill Modularization](https://mlsanity.com/paper/2502.14140/) (2025)
- [InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs](https://mlsanity.com/paper/2512.07410/) (2025)
- [SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control](https://mlsanity.com/paper/2605.22894/) (2026)
- [Learning to Control Physically-simulated 3D Characters via Generating and Mimicking 2D Motions](https://mlsanity.com/paper/2512.08500/) (2025)
- [UniCross: Unified Cross-Skill Dexterous Manipulation Synthesis](https://mlsanity.com/paper/2607.28198/) (2026)
- [MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control](https://mlsanity.com/paper/2605.26006/) (2026)
- [Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation](https://mlsanity.com/paper/2503.18531/) (2025)
- [LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction](https://mlsanity.com/paper/2609.19688/) (2026)
- [DexMimic: A Generalist Dexterous Hand-Object Tracking Policy via Value-Guided Reset Allocation](https://mlsanity.com/paper/2610.19089/) (2026)

## Abstract (arXiv)

Physically-simulated models for human motion can generate high-quality responsive character animations, often in real-time. Natural language serves as a flexible interface for controlling these models, allowing expert and non-expert users to quickly create and edit their animations. Many recent physics-based animation methods, including those that use text interfaces, train control policies using reinforcement learning (RL). However, scaling these methods beyond several hundred motions has remained challenging. Meanwhile, kinematic animation models are able to successfully learn from thousands of diverse motions by leveraging supervised learning methods. Inspired by these successes, in this work we introduce SuperPADL, a scalable framework for physics-based text-to-motion that leverages both RL and supervised learning to train controllers on thousands of diverse motion clips. SuperPADL is trained in stages using progressive distillation, starting with a large number of specialized experts using RL. These experts are then iteratively distilled into larger, more robust policies using a combination of reinforcement learning and supervised learning. Our final SuperPADL controller is trained on a dataset containing over 5000 skills and runs in real time on a consumer GPU. Moreover, our policy can naturally transition between skills, allowing for users to interactively craft multi-stage animations. We experimentally demonstrate that SuperPADL significantly outperforms RL-based baselines at this large data scale.