TalkRL: Reinforcement Learning Interviews

Eugene Vinitsky is a PhD student at UC Berkeley advised by Alexandre Bayen. He has interned at Tesla and Deepmind. Featured ReferencesA learning agent that acquires social norms from public sanctions in decentralized multi-agent settingsEugene Vinitsky, Raphael Köster, John P. Agapiou, Edgar Duéñez-Guzmán, Alexander Sasha Vezhnevets, Joel Z. LeiboOptimizing Mixed Autonomy Traffic Flow With Decentralized Autonomous Vehicles and Multi-Agent RLEugene Vinitsky, Nathan Lichtle, Kanaad Parvate, Alexandre BayenLagrangian Control through Deep-RL: Applications to Bottleneck DecongestionEugene Vinitsky; Kanaad Parvate; Aboudy Kreidieh; Cathy Wu; Alexandre Bayen 2018The Surprising Effectiveness of PPO in Cooperative Multi-Agent GamesChao Yu, Akash Velu, Eugene Vinitsky, Yu Wang, Alexandre Bayen, Yi WuAdditional ReferencesSUMO: Simulation of Urban MObility