Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
–Neural Information Processing Systems
Unlike most reinforcement learning agents which require an unrealistic amount of environment interactions to learn a new behaviour, humans excel at learning quickly by merely observing and imitating others.
Neural Information Processing Systems
Oct-9-2025, 01:28:51 GMT
- Country:
- Asia > China (0.04)
- Europe
- North America
- Canada > Alberta
- United States > Minnesota
- Hennepin County > Minneapolis (0.14)
- Genre:
- Research Report (0.46)
- Industry:
- Leisure & Entertainment > Games (0.46)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Neural Networks > Deep Learning (1.00)
- Reinforcement Learning (1.00)
- Natural Language (1.00)
- Representation & Reasoning (1.00)
- Robots (0.94)
- Machine Learning
- Information Technology > Artificial Intelligence