Aryaman Reddi

Aryaman Reddi is a PhD student at TU Darmstadt affiliated with the Intelligent Autonomous Systems (IAS) group within the Department of Computer Science. He is also associated with the JMU Würzburg LiteRL Lab and the Hessian Centre for Artificial Intelligence.

Reddi earned his BA and MEng in Information and Computer Engineering from the University of Cambridge, where his Master's thesis explored deep Q-learning for game strategies under bounded rationality.

His research focuses on multi-agent reinforcement learning, game theory, and bounded rationality, aiming to enhance agent generalizability and dynamic obstacle avoidance. His work intersects deep learning and cognitive science with applications in robotics and humanoid systems.

Key publications include contributions to the ICLR 2024 conference and the CoRL 2024 LocoLearn Workshop, both addressing adversarial reinforcement learning under bounded rationality frameworks.

Reddi is actively involved in academic collaboration, working with researchers like Prof. Carlo D'Eramo at TU Darmstadt and Prof. Glenn Vinnicombe at Cambridge. His projects explore robot learning algorithms, humanoid motion planning, and AI ethics in autonomous systems.