Three Questions that Keep Me Up at Night | Eric Jang
evjang.com · 1,262 words · saved by 4 readers
Q1: Can we imitate “thinking” from only observing behavior?
Q1: Can we imitate "thinking" from only observing behavior? Suppose you have a large fleet of autonomous vehicles with human operators driving them around diverse road conditions. We can observe the decisions made by the human, and attempt to use imitation learning algorithms to map robot observations to the steering decisions that the human would take. However, we can't observe what the homunculus is thinking directly. Humans read road text and other signage to interpret what they should and should not do. Humans plan more carefully when doing tricky maneuvers (parallel parking). Humans feel
saved by
related reading
- How Can We Make Robotics More like Generative Modeling? | Eric Jangevjang.com
- As Rocks May Think | Eric Jangevjang.com
- Just Ask for Generalization | Eric Jangevjang.com
- To Understand Language is to Understand Generalization | Eric Jangevjang.com
- Book: AI is Good for You | Eric Jangevjang.com
- All Roads Lead to Robotics | Eric Jangevjang.com
- Can LLMs Critique and Iterate on Their Own Outputs? | Eric Jangevjang.com
- Simulators — LessWronglesswrong.com
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- You can’t imitation-learn how to continual-learn — LessWronglesswrong.com
- Eric Jangevjang.com
- Deep Deceptiveness — LessWronglesswrong.com