Amin Rakhsha

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 11

Top Topics

Reinforcement Learning

Maximum Entropy

Top Venues

J. Mach. Learn. Res.

Publications

Amin Rakhsha, Mete Kemertas, Mohammad Ghavamzadeh, Amir-massoud Farahmand
Maximum Entropy Model Correction in Reinforcement Learning. ICLR (2024)
Mark Bedaywi, Amin Rakhsha, Amir-massoud Farahmand
PID Accelerated Temporal Difference Algorithms. CoRR (2024)
Jongmin Lee, Amin Rakhsha, Ernest K. Ryu, Amir-massoud Farahmand
Deflated Dynamics Value Iteration. CoRR (2024)
Amin Rakhsha, Mete Kemertas, Mohammad Ghavamzadeh, Amir-massoud Farahmand
Maximum Entropy Model Correction in Reinforcement Learning. CoRR (2023)
Amin Rakhsha, Andrew Wang, Mohammad Ghavamzadeh, Amir-massoud Farahmand
Operator Splitting Value Iteration. NeurIPS (2022)
Amin Rakhsha, Andrew Wang, Mohammad Ghavamzadeh, Amir-massoud Farahmand
Operator Splitting Value Iteration. CoRR (2022)
Amin Rakhsha, Xuezhou Zhang, Xiaojin Zhu, Adish Singla
Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments. CoRR (2021)
Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla
Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks. J. Mach. Learn. Res. 22 (2021)
Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla
Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning. CoRR (2020)
Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla
Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks. CoRR (2020)
Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla
Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning. ICML (2020)