Video Prediction Models as Rewards for Reinforcement Learning
–Neural Information Processing Systems
Specifying reward signals that allow agents to learn complex behaviors is a longstanding challenge in reinforcement learning.
Neural Information Processing Systems
Nov-19-2025, 21:44:17 GMT
- Country:
- Asia > Japan
- Honshū > Chūbu > Ishikawa Prefecture > Kanazawa (0.04)
- North America
- Canada (0.04)
- United States > California
- Alameda County > Berkeley (0.04)
- South America > Chile
- Asia > Japan
- Genre:
- Research Report (0.46)
- Industry:
- Education (0.68)
- Technology: