Aryaman Reddi
Research Interests
Multi Agent Reinforcement Learning, Game Theory, Cognitive Science, Genetics, and Deep Learning
Affiliations
1. JMU Würzburg, LiteRL Lab
2. TU Darmstadt, Intelligent Autonomous Systems, Computer Science Department
3. Hessian Centre for Artificial Intelligence
Contact
aryaman(dot)reddi(at)tu-darmstadt(dot)de
Room E327, Building S2|02, TU Darmstadt, FB-Informatik, FG-IAS, Hochschulstr. 10, 64289 Darmstadt
I'm Aryaman, a PhD student interested in multi-agent reinforcement learning and game theory. I'm based in TU Darmstadt and I'm supervised by Professor Carlo D'Eramo of the LiteRL group.
I studied Information and Computer Engineering at the University of Cambridge, where I received my BA and MEng. My Master's thesis, titled "Deep Q-Learning for Congruent Non-Dominated Game Strategies", investigated the generalisability of deep Q-learning agents under bounded rationality, and was supervised by Professor Glenn Vinnicombe of the Control Group.
Publications
-
- Reddi, A.; Toelle, M.; Peters, J.; Chalvatzaki, G.; D'Eramo, C. (2024). Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula, International Conference on Learning Representations (ICLR), Spotlight.
-
- Holgado-Alvarez, J.H.; Reddi, A.; D'Eramo, C. (2024). Dynamic Obstacle Avoidance with Bounded Rationality Adversarial Reinforcement Learning, CoRL 2024 Locolearn Workshop.