Abhishek Naik
@abhisheknaik96.bsky.social
PhD graduate in reinforcement learning from the University of Alberta. Now, RL research in space! 🚀🛰️
We had a delightful conversation covering:
⏺️ how I chose my PhD topic,
⏺️ connections with cognitive psychology and neuroscience,
⏺️ why I'm applying RL/AI in space today,
⏺️ what got me interested in machine learning in the first place,
and more!
Thank you, @robinchauhan.bsky.social!
⏺️ how I chose my PhD topic,
⏺️ connections with cognitive psychology and neuroscience,
⏺️ why I'm applying RL/AI in space today,
⏺️ what got me interested in machine learning in the first place,
and more!
Thank you, @robinchauhan.bsky.social!
E62: Abhishek Naik on Continuing RL & Average Reward
How should RL handle non-episodic tasks, like Mars rovers or HPC scheduling? @abhisheknaik96.bsky.social shares insights from his PhD with Rich Sutton, plus how almost every discounted-reward algorithm can be improved by reward centering.
How should RL handle non-episodic tasks, like Mars rovers or HPC scheduling? @abhisheknaik96.bsky.social shares insights from his PhD with Rich Sutton, plus how almost every discounted-reward algorithm can be improved by reward centering.
February 11, 2025 at 10:04 PM
We had a delightful conversation covering:
⏺️ how I chose my PhD topic,
⏺️ connections with cognitive psychology and neuroscience,
⏺️ why I'm applying RL/AI in space today,
⏺️ what got me interested in machine learning in the first place,
and more!
Thank you, @robinchauhan.bsky.social!
⏺️ how I chose my PhD topic,
⏺️ connections with cognitive psychology and neuroscience,
⏺️ why I'm applying RL/AI in space today,
⏺️ what got me interested in machine learning in the first place,
and more!
Thank you, @robinchauhan.bsky.social!