PlanninginMarkovDecisionProcesseswith Gap-DependentSampleComplexity
–Neural Information Processing Systems
This problem-dependent sample complexityresult is expressed in terms of the sub-optimality gapsof the state-action pairs that are visited during exploration.
Neural Information Processing Systems
Feb-7-2026, 11:33:10 GMT
- Country:
- North America > Canada
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- Ontario > Toronto (0.04)
- British Columbia > Metro Vancouver Regional District
- North America > Canada
- Technology: