The Need for a Big World Simulator: A Scientific Challenge for Continual Learning
This is experimental HTML to improve accessibility. We invite you to report rendering errors. Use Alt+Y to toggle on accessible reporting links and Alt+Shift+Y to toggle off. Learn more about this project and help improve conversions.
The Need for a Big World Simulator: A Scientific Challenge for Continual Learning Saurabh Kumar 1 1 1 Equal contribution. szk@stanford.edu Department of Computer Science Stanford University ∗ Denotes equal contribution. &Hong Jun Jeon ∗ hjjeon@stanford.edu Department of Computer Science Stanford University &Alex Lewandowski lewandowski@ualberta.ca Department of Computing Science University of Alberta &Benjamin Van Roy bvr@stanford.edu Department of Electrical Engineering Stanford University Abstract The “small agent, big world” frame offers a conceptual view that motivates the need for continu
related reading
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- pdfopenreview.net
- You can’t imitation-learn how to continual-learn — LessWronglesswrong.com
- Why We Need Continual Learning | Andreessen Horowitza16z.com
- Learning Beyond Gradientstrinkle23897.github.io
- Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RLarxiv.org
- The Continual Learning Problemjessylin.com
- The Pitfalls of Imitation Learning when Actions are Continuousarxiv.org
- 1011.0686arxiv.org
- [2302.00487] A Comprehensive Survey of Continual Learning: Theory, Method and Applicationarxiv.org
- Reinforcement Learning in Newcomblike Problemsproceedings.neurips.cc
- Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learningarxiv.org