14 citations · 23 across the 10 of their papers we have counts for
10 papers
Learning Robust Social Strategies with Large Language Models
Dereck Piche, Mohammed Muqeeth, Milad Aghajohari +3
As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challeng…
The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning
Milad Aghajohari, Kamran Chitsaz, Amirhossein Kazemnejad +4
Reinforcement learning (RL) has recently become a strong recipe for training reasoning LLMs that produce long chains of thought (LongCoT). Yet the standard RL "thinking environment…
DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
Sara Vera Marjanović, Arkil Patel, Vaibhav Adlakha +14
Large Reasoning Models like DeepSeek-R1 mark a fundamental shift in how LLMs approach complex problems. Instead of directly producing an answer for a given input, DeepSeek-R1 creat…
VinePPO: Refining Credit Assignment in RL Training of LLMs
Amirhossein Kazemnejad, Milad Aghajohari, Eva Portelance +4
Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receiving any reward. Properly assigning credit…
Advantage Alignment Algorithms
Juan Agustin Duque, Milad Aghajohari, Tim Cooijmans +4
Artificially intelligent agents are increasingly being integrated into human decision-making: from large language model (LLM) assistants to autonomous vehicles. These systems often…
LOQA: Learning with Opponent Q-Learning Awareness
Milad Aghajohari, Juan Agustin Duque, Tim Cooijmans +1
In various real-world scenarios, interactions among agents often resemble the dynamics of general-sum games, where each agent strives to optimize its own utility. Despite the ubiqu…
Best Response Shaping
Milad Aghajohari, Tim Cooijmans, Juan Agustin Duque +2
We investigate the challenge of multi-agent deep reinforcement learning in partially competitive environments, where traditional methods struggle to foster reciprocity-based cooper…
Meta-Value Learning: a General Framework for Learning with Learning Awareness
Tim Cooijmans, Milad Aghajohari, Aaron Courville
Gradient-based learning in multi-agent systems is difficult because the gradient derives from a first-order model which does not account for the interaction between agents' learnin…
Riemannian Diffusion Models
Chin-Wei Huang, Milad Aghajohari, Avishek Joey Bose +2
Diffusion models are recent state-of-the-art methods for image generation and likelihood estimation. In this work, we generalize continuous-time diffusion models to arbitrary Riema…
Determinacy in Discrete-Bidding Infinite-Duration Games
Milad Aghajohari, Guy Avni, Thomas A. Henzinger
In two-player games on graphs, the players move a token through a graph to produce an infinite path, which determines the winner of the game. Such games are central in formal metho…