Publications

2026

1. Findings ACL

   LUMINA: Long-horizon Understanding for Multi-turn Interactive Agents

   Amin Rakhsha, Thomas Hehn, Pietro Mazzaglia, Fabio Valerio Massoli, Arash Behboodi, and Tribhuvanesh Orekondy

   In Findings of the Association for Computational Linguistics: ACL 2026, Jul 2026

   arXiv Bib HTML PDF

   @inproceedings{rakhsha2026lumina,
     title = {{LUMINA}: Long-horizon Understanding for Multi-turn Interactive Agents},
     author = {Rakhsha, Amin and Hehn, Thomas and Mazzaglia, Pietro and Massoli, Fabio Valerio and Behboodi, Arash and Orekondy, Tribhuvanesh},
     booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
     month = jul,
     year = {2026},
     address = {San Diego, California, United States},
     publisher = {Association for Computational Linguistics},
     pages = {3913--3926},
     doi = {10.18653/v1/2026.findings-acl.190},
   }

2025

1. NeurIPS

   Majority of the Bests: Improving Best-of-N via Bootstrapping

   Amin Rakhsha, Kanika Madan, Tianyu Zhang, Amir-massoud Farahmand, and Amir Khasahmadi

   In Advances in Neural Information Processing Systems, 2025

   arXiv Bib HTML PDF Code

   @inproceedings{rakhsha2025majority,
     title = {Majority of the Bests: Improving {Best-of-N} via Bootstrapping},
     author = {Rakhsha, Amin and Madan, Kanika and Zhang, Tianyu and Farahmand, Amir-massoud and Khasahmadi, Amir},
     booktitle = {Advances in Neural Information Processing Systems},
     volume = {38},
     pages = {37844--37877},
     year = {2025},
     publisher = {Curran Associates, Inc.},
     doi = {10.52202/085713-1268},
   }

2. TMLR

   Deflated Dynamics Value Iteration

   Jongmin Lee^†, Amin Rakhsha, Ernest K. Ryu, and Amir-massoud Farahmand

   Transactions on Machine Learning Research, 2025

   arXiv Bib HTML PDF Code

   @article{lee2025deflated,
     title = {Deflated Dynamics Value Iteration},
     author = {Lee, Jongmin and Rakhsha, Amin and Ryu, Ernest K. and Farahmand, Amir-massoud},
     journal = {Transactions on Machine Learning Research},
     year = {2025},
   }

2024

1. RLC

   PID Accelerated Temporal Difference Algorithms

   Mark Bedaywi^*†, Amin Rakhsha^*, and Amir-massoud Farahmand

   Reinforcement Learning Journal, 2024

   arXiv Bib HTML PDF Code

   @article{bedaywi2024pid,
     title = {{PID} Accelerated Temporal Difference Algorithms},
     author = {Bedaywi, Mark and Rakhsha, Amin and Farahmand, Amir-massoud},
     journal = {Reinforcement Learning Journal},
     volume = {5},
     pages = {2071--2095},
     year = {2024},
   }

2. ICLR

   Maximum Entropy Model Correction in Reinforcement Learning

   Amin Rakhsha, Mete Kemertas, Mohammad Ghavamzadeh, and Amir-massoud Farahmand

   In The Twelfth International Conference on Learning Representations, 2024

   arXiv Bib HTML PDF Code

   @inproceedings{rakhsha2024maximum,
     title = {Maximum Entropy Model Correction in Reinforcement Learning},
     author = {Rakhsha, Amin and Kemertas, Mete and Ghavamzadeh, Mohammad and Farahmand, Amir-massoud},
     booktitle = {The Twelfth International Conference on Learning Representations},
     year = {2024},
   }

2022

1. NeurIPS

   Operator Splitting Value Iteration

   Amin Rakhsha, Andrew Wang^†, Mohammad Ghavamzadeh, and Amir-massoud Farahmand

   In Advances in Neural Information Processing Systems, 2022

   arXiv Bib HTML PDF Code

   @inproceedings{rakhsha2022operator,
     title = {Operator Splitting Value Iteration},
     author = {Rakhsha, Amin and Wang, Andrew and Ghavamzadeh, Mohammad and Farahmand, Amir-massoud},
     booktitle = {Advances in Neural Information Processing Systems},
     volume = {35},
     pages = {38373--38385},
     year = {2022},
     publisher = {Curran Associates, Inc.},
     doi = {10.52202/068431-2780},
   }

2021

1. NeurIPS WS

   Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments

   Amin Rakhsha^*, Xuezhou Zhang^*, Xiaojin Zhu, and Adish Singla

   In NeurIPS Workshop on Learning and Decision-Making with Strategic Feedback, 2021

   arXiv Bib HTML PDF

   @inproceedings{rakhsha2021reward,
     title = {Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments},
     author = {Rakhsha, Amin and Zhang, Xuezhou and Zhu, Xiaojin and Singla, Adish},
     booktitle = {NeurIPS Workshop on Learning and Decision-Making with Strategic Feedback},
     year = {2021},
   }

2. JMLR

   Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks

   Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, and Adish Singla

   Journal of Machine Learning Research, 2021

   arXiv Bib HTML PDF Code

   @article{rakhsha2021policy,
     title = {Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks},
     author = {Rakhsha, Amin and Radanovic, Goran and Devidze, Rati and Zhu, Xiaojin and Singla, Adish},
     journal = {Journal of Machine Learning Research},
     volume = {22},
     number = {210},
     pages = {1--45},
     year = {2021},
   }

2020

1. ICML

   Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning

   Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, and Adish Singla

   In Proceedings of the 37th International Conference on Machine Learning, 13–18 jul 2020

   arXiv Bib HTML PDF Code

   @inproceedings{rakhsha2020policy,
     title = {Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning},
     author = {Rakhsha, Amin and Radanovic, Goran and Devidze, Rati and Zhu, Xiaojin and Singla, Adish},
     booktitle = {Proceedings of the 37th International Conference on Machine Learning},
     editor = {Daum\'{e} III, Hal and Singh, Aarti},
     volume = {119},
     series = {Proceedings of Machine Learning Research},
     pages = {7974--7984},
     month = {13--18 Jul},
     year = {2020},
     publisher = {PMLR},
   }