# AdaptNet: Policy Adaptation for Physics-Based Character Control

arXiv: https://arxiv.org/abs/2310.00239 · HTML: https://mlsanity.com/paper/2310.00239/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 83 references that are in the map.
- First posted on arXiv 30 Sep 2023.

## Builds on (most cited first, 30 of 61)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [Reinforcement Learning with Deep Energy-Based Policies](https://mlsanity.com/paper/1702.08165/) (2017)
- [Learning to learn by gradient descent by gradient descent](https://mlsanity.com/paper/1606.04474/) (2016)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [Measuring the Intrinsic Dimension of Objective Landscapes](https://mlsanity.com/paper/1804.08838/) (2018)
- [The Intrinsic Dimension of Images and Its Impact on Learning](https://mlsanity.com/paper/2104.08894/) (2021)
- [On the "steerability" of generative adversarial networks](https://mlsanity.com/paper/1907.07171/) (2019)
- [Geometric GAN](https://mlsanity.com/paper/1705.02894/) (2017)

## Built on by (most cited first, 16 of 16)

- [TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization](https://mlsanity.com/paper/2503.19901/) (2025)
- [SMooDi: Stylized Motion Diffusion Model](https://mlsanity.com/paper/2407.12783/) (2024)
- [PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios](https://mlsanity.com/paper/2404.19722/) (2024)
- [Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns](https://mlsanity.com/paper/2410.20389/) (2024)
- [Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey](https://mlsanity.com/paper/2404.17070/) (2024)
- [Learning to Ball: Composing Policies for Long-Horizon Basketball Moves](https://mlsanity.com/paper/2509.22442/) (2025)
- [From Words to Worlds: Transforming One-line Prompt into Immersive Multi-modal Digital Stories with Communicative LLM Agent](https://mlsanity.com/paper/2406.10478/) (2024)
- [CBIL: Collective Behavior Imitation Learning for Fish from Real Videos](https://mlsanity.com/paper/2504.00234/) (2025)
- [ChatDyn: Language-Driven Multi-Actor Dynamics Generation in Street Scenes](https://mlsanity.com/paper/2412.08685/) (2024)
- [Versatile Physics-based Character Control with Hybrid Latent Representation](https://mlsanity.com/paper/2503.12814/) (2025)
- [Environment-aware Motion Matching](https://mlsanity.com/paper/2510.22632/) (2025)
- [MUSIC: Learning Muscle-Driven Dexterous Hand Control](https://mlsanity.com/paper/2604.23886/) (2026)
- [IAM: Identity-Aware Human Motion and Shape Joint Generation](https://mlsanity.com/paper/2604.25164/) (2026)
- [MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters](https://mlsanity.com/paper/2603.29272/) (2026)
- [NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control](https://mlsanity.com/paper/2605.20209/) (2026)
- [Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics](https://mlsanity.com/paper/2606.22806/) (2026)

## Abstract (arXiv)

Motivated by humans' ability to adapt skills in the learning of new ones, this paper presents AdaptNet, an approach for modifying the latent space of existing policies to allow new behaviors to be quickly learned from like tasks in comparison to learning from scratch. Building on top of a given reinforcement learning controller, AdaptNet uses a two-tier hierarchy that augments the original state embedding to support modest changes in a behavior and further modifies the policy network layers to make more substantive changes. The technique is shown to be effective for adapting existing physics-based controllers to a wide range of new styles for locomotion, new task targets, changes in character morphology and extensive changes in environment. Furthermore, it exhibits significant increase in learning efficiency, as indicated by greatly reduced training times when compared to training from scratch or using other approaches that modify existing policies. Code is available at https://motion-lab.github.io/AdaptNet.