NearInstance-OptimalPACReinforcementLearning forDeterministicMDPs
–Neural Information Processing Systems
Whileminimax optimal algorithms exist for this problem, its instance-dependent complexity remains elusiveinepisodic Markovdecision processes (MDPs).
Neural Information Processing Systems
Feb-8-2026, 09:35:26 GMT
- Country:
- Europe > France
- Auvergne-Rhône-Alpes > Lyon
- Lyon (0.04)
- Hauts-de-France > Nord
- Lille (0.04)
- Île-de-France > Paris
- Paris (0.04)
- Auvergne-Rhône-Alpes > Lyon
- Europe > France
- Genre:
- Research Report (0.46)
- Technology: