[IEEE TNNLS 2025] Bicriteria Policy Optimization for High Accuracy Reinforcement Learning

A PyTorch implementation of the gradient fusion strategy for Bicriteria Policy Optimization. This approach is specifically designed for optimization problems where two objectives share a common global optimum, such as combining Reinforcement Learning (RL) and Imitation Learning (IL).

Bibtex citation

If you find our work useful, please cite our paper:

@article{zhan2025bicriteria,
  title={Bicriteria policy optimization for high-accuracy reinforcement learning},
  author={Zhan, Guojian and Zhang, Xiangteng and Zhang, Feihong and Tao, Letian and Li, Shengbo Eben},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2025},
  publisher={IEEE}
}