Jalal Etesami

Papers

Total Citations

H-Index

About

Jalal Etesami is a researcher working at the intersection of reinforcement learning, multi-agent systems, and machine learning theory. His work tackles some of the most challenging problems in sequential decision-making, particularly how intelligent agents can learn effective behaviors from limited data and interact strategically in complex environments. Etesami's most recognized contribution is his 2019 paper on Wasserstein Adversarial Imitation Learning, which has garnered 35 citations. This work advances the field of imitation learning by addressing a fundamental limitation in inverse reinforcement learning: the reliance on problem-dependent reward functions. By leveraging Wasserstein distance as a principled framework, his approach offers a more flexible and generalizable method for recovering expert policies from demonstrations, significantly improving sample efficiency. His 2020 work on non-cooperative multi-agent systems introduces a prescriptive model grounded in Markov game theory, addressing the realistic scenario where agents operate without full knowledge of one another's strategies. This contributes meaningfully to fields ranging from distributed robotics to economics. Etesami's research reflects a strong commitment to bridging theoretical rigor with practical applicability, making his work valuable for students and researchers interested in modern reinforcement learning and game-theoretic machine learning.