Machine Learning Street Talk (MLST)

#114 - Secrets of Deep Reinforcement Learning (Minqi Jiang)

100 snips
Apr 16, 2023
Minqi Jiang, a PhD student at University College London and Meta AI, explores the intriguing realm of deep reinforcement learning. He shares insights on balancing serendipity with planning in research, along with the implications of Goodhart's Law in decision-making. The discussion dives into the complexities of emergent intelligence and the potential of language models. Minqi highlights the shift towards Software 2.0, challenges in interpretability, and the importance of open-ended research, offering a thought-provoking glimpse into the future of AI technology.
Ask episode
AI Snips
Chapters
Books
Transcript
Episode notes
ANECDOTE

Career Journey

  • Minqi Jiang, a PhD student at UCL and Meta AI, shared his career journey.
  • It included working at Google Translate, Android (Google Fit), and founding Hyper Travel, a travel concierge startup.
ADVICE

Value of Foundational Knowledge

  • Foundational knowledge from textbooks like "PRML" and "Sutton and Barto" is important.
  • It provides a basis for understanding complex ML concepts.
ANECDOTE

Startup Experience

  • Minqi Jiang and his co-founder bootstrapped Hyper Travel with savings, iterating through app ideas.
  • One, "Once," a diary-like social media app, foreshadowed BeReal's core concept.
Get the Snipd Podcast app to discover more snips from this episode
Get the app