Learning General World Models in a Handful of Reward-Free Deployments Yingchen Xu UCL, FAIR Jack Parker-Holder University of Oxford Aldo Pacchiano Microsoft Research Philip J. Ball
–Neural Information Processing Systems
Combining these two properties, we introduce the reward-free deployment efficiency setting, a new paradigm for RL research.
Neural Information Processing Systems
Aug-17-2025, 14:10:15 GMT
- Country:
- North America > United States
- Massachusetts > Middlesex County > Cambridge (0.04)
- Europe
- France (0.04)
- United Kingdom > England
- Oxfordshire > Oxford (0.40)
- Asia > Middle East
- Jordan (0.04)
- North America > United States
- Genre:
- Research Report (0.93)
- Overview (0.67)
- Industry:
- Education (0.68)
- Leisure & Entertainment > Games (0.46)
- Technology: