551: Deep Reinforcement Learning — with Wah Loon Keng
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Challenges and Applications of Deep Reinforcement Learning in Real-World Scenarios
The chapter explores the complexities of reward design in reinforcement learning in practical settings like driving, stressing the importance of careful reward signal design to avoid undesired AI behavior. It showcases applications of deep reinforcement learning in diverse fields such as robotics, logistics, and energy management, discussing the challenges of data requirements for training in real-world scenarios. The chapter also covers the development of the SLM lab framework for organizing deep RL algorithms and the speaker's experience as an AI engineer, highlighting the significance of data engineering and deployment in the data science field.
Play episode from 50:37
Transcript
