2024 Vineppo: Unlocking RL’s Potential for LLM Reasoning Through Refined Credit Assignment Amirhossein Kazemnejad*, Milad Aghajohari*, Eva Portelance, and 4 more authors arXiv preprint arXiv:2410.01679, 2024 Best Response Shaping Milad Aghajohari, Tim Cooijmans, Juan Agustin Duque, and 2 more authors RLC 2024, 2024 LOQA: Learning with Opponent Q-Learning Awareness Milad Aghajohari, Juan Agustin Duque, Tim Cooijmans, and 1 more author arXiv 2024, 2024 Advantage Alignment Algorithms Juan Agustin Duque, Milad Aghajohari, Tim Cooijmans, and 4 more authors arXiv 2024, 2024 2023 Differentiable Best Response Shaping(Thesis) Milad Aghajohari Université de Montréal, 2023 Meta-Value Learning: a General Framework for Learning with Learning Awareness Tim Cooijmans, Milad Aghajohari, and Aaron Courville arXiv 2023, 2023 2022 Riemannian Diffusion Models Chin-Wei Huang, Milad Aghajohari, Joey Bose, and 2 more authors NeurIPS 2022, 2022 2021 Determinacy in Discrete-Bidding Infinite-Duration Games Milad Aghajohari, Guy Avni, and Thomas A Henzinger Logical Methods in Computer Science, 2021 Degree-based Feature Is All You Need: Science4Cast Report Milad Aghajohari, Mohammad Sadegh Akhondzadeh, Saleh Ashkboos, and 1 more author In IEEE International Conference on Big Data, 2021, 2021