Pass@KPolicy Optimization: Solving Harder Reinforcement Learning Problems
–Neural Information Processing Systems
Reinforcement Learning algorithms commonly sample multiple (n > 1) solution attempts for each problem and reward them independently.
Neural Information Processing Systems
Jun-22-2026, 23:32:45 GMT
- Country:
- Asia (0.28)
- Genre:
- Research Report > Experimental Study (1.00)
- Industry:
- Information Technology (0.46)
- Education > Focused Education
- Special Education (0.40)
- Technology: