---
language:
- en
pipeline_tag: reinforcement-learning
---
# Error Amplification Limits ANN-to-SNN Conversion in Continuous Control

Official **model** release for the **ICML 2026** paper [[`arXiv`](https://arxiv.org/pdf/2601.21778)] [[`GitHub`](https://github.com/xuzijie32/ANN2SNN-CRPI)]


# Well-trained ANN Models
The models for DDPG/TD3/SAC agents trained on MuJoCo for 3M steps are stored in `./DDPG&TD3&SAC_MuJoCo/models`.

The models for DrQ-v2 agents trained on DMC are stored in `./DrQ-v2_DMC/exp_local`.

# More Details 
Code is available at this [GitHub repository](https://github.com/xuzijie32/ANN2SNN-CRPI). You can also view our [paper PDF](https://arxiv.org/pdf/2601.21778).

# Citing This

```bibtex
@article{xu2026error,
  title={Error Amplification Limits ANN-to-SNN Conversion in Continuous Control},
  author={Xu, Zijie and Huang, Zihan and Dong, Yiting and Chen, Kang and Liu, Wenxuan and Yu, Zhaofei},
  journal={arXiv preprint arXiv:2601.21778},
  year={2026}
}
```