What are your interests?
Select categories to help us recommend content for you.
Let's Go!
Close queue History
Play full episodes to fill your queue.
Fathom beta logo
   
mute button
Emergent Behavior in Collective Intelligences
episode icon Machine Learning Street Talk (MLST)
#114 - Secrets of Deep Reinforcement Learning (Minqi Jiang)
Patreon: https://www.patreon.com/mlst Discord: https... more
Apr 16 2023 2h 47m
Emergent Behavior in Collective Intelligences
Chapter 1 3 mins
Tech & Startup Background
Chapter 2 7 mins
Pursuing PhD in Deep RL
Chapter 3 56 sec
Startup Lessons
Chapter 4 6 mins
Serendipity vs Planning
Chapter 5 3 mins
Objectives & Decision Making
Chapter 6 3 mins
Minimax Regret & Uncertainty
Chapter 7 7 mins
Robustness in RL & Zero-Sum Games
Chapter 8 7 mins
RL vs Supervised Learning
Chapter 9 5 mins
Exploration & Intelligence
Chapter 10 7 mins
Environment, Emergence, Abstraction
Chapter 11 10 mins
Open-endedness & Intelligence Explosion
Chapter 12 11 mins
Language Models & Training Data
Chapter 13 10 mins
RLHF & Language Models
Chapter 14 13 mins
Creativity in Language Models
Chapter 15 4 mins
Limitations of RL
Chapter 16 3 mins
Software 2.0 & Interpretability
Chapter 17 3 mins
Language Models & Code Reliability
Chapter 18 4 mins
Robust Prioritized Level Replay
Chapter 19 12 mins
Open-ended Learning
Chapter 20 22 mins
Auto-curriculum & Deep RL
Chapter 21 5 mins
Robotics & Open-ended Learning
Chapter 22 5 mins
Learning Potential & MDPs
Chapter 23 45 sec
Universal Function Space
Chapter 24 1 min
Goal-Directed Learning & Auto-Curricula
Chapter 25 2 mins
Advice & Closing Thoughts
Like
Clip
Share
Transcript
More
Play Full