Скачать или смотреть Akhil Bagaria - Learning Abstractions for Exploration and Planning

To create generally capable, intelligent machines, we must equip our agents with the ability to autonomously acquire their own abstractions. My research addresses this question using tools from reinforcement learning and planning. In this talk, I will discuss ways in which agents may discover temporally-extended abstract actions (or options). Next, I will discuss how discovered options induce a form of state abstraction, which can be used for planning. Finally, I will discuss how the discovery of abstract states and actions can be interleaved in a never-ending cycle to create agents that continually increase their competence in the world.

Akhil Bagaria is a Senior Applied Scientist at Amazon, working on the RL for the Amazon supply chain. He recently got his PhD from Brown University working on reinforcement learning with George Konidaris. He was an intern on the RL team at DeepMind London, where he worked with Tom Schaul on goal-based exploration. Prior to that, he worked on the multitouch team at Apple where he developed gesture recognition algorithms that are currently shipping on all Macbooks and iPads. He did his undergrad from Harvey Mudd College, where he received the JRR Phillips Award for outstanding engineering judgement and conducted research which included tracking sharks with autonomous underwater robots.

This session is brought to you by the Cohere Labs Open Science Community - a space where ML researchers, engineers, linguists, social scientists, and lifelong learners connect and collaborate with each other. We'd like to extend a special thank you to Rahul Narava
Gusti Winata, Leads of our Reinforcement Learning group for their dedication in organizing this event.

If you’re interested in sharing your work, we welcome you to join us! Simply fill out the form at https://forms.gle/ALND9i6KouEEpCnz6 to express your interest in becoming a speaker.

Join the Cohere Labs Open Science Community to see a full list of upcoming events (https://tinyurl.com/CohereLabsCommuni....