

Abhishek Naik on Continuing RL & Average Reward
Feb 10, 2025
Abhishek Naik, a postdoctoral fellow at the National Research Council of Canada, recently completed his PhD in reinforcement learning under Rich Sutton. He explores average reward methods and their implications for continuous decision-making in AI. The discussion dives into innovative applications in space exploration and challenges in resource allocation, drawing on examples like Mars rovers. Abhishek emphasizes the transformative power of first-principles thinking, highlighting how AI advancements are shaping the future of spacecraft control and missions.
Chapters
Books
Transcript
Episode notes
1 2 3 4 5 6 7
Intro
00:00 • 2min
Navigating Decision-Making in Reinforcement Learning
02:10 • 19min
Evolving Average Reward Methods in Reinforcement Learning
20:49 • 17min
Discounted vs. Average Reward Algorithms
37:49 • 13min
Transformative Insights Through First-Principles Thinking
50:58 • 3min
Innovations in AI and Space Exploration
54:14 • 24min
Emphasizing Growth Through Learning and Connection
01:17:51 • 4min