Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design Michael Dennis
–Neural Information Processing Systems
A wide range of reinforcement learning (RL) problems -- including robustness, transfer learning, unsupervised RL, and emergent complexity -- require specifying a distribution of tasks or environments in which a policy will be trained.
Neural Information Processing Systems
Nov-14-2025, 15:27:05 GMT
- Country:
- Europe
- Slovenia > Drava
- Municipality of Benedikt > Benedikt (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Slovenia > Drava
- North America
- Canada (0.04)
- United States
- California
- Alameda County > Berkeley (0.14)
- Santa Clara County > Mountain View (0.04)
- New Jersey (0.04)
- California
- Europe
- Genre:
- Research Report > New Finding (0.68)
- Industry:
- Education (1.00)
- Technology: