AgnosticQ-learningwithFunctionApproximationin DeterministicSystems: Near-OptimalBoundson ApproximationErrorandSampleComplexity
–Neural Information Processing Systems
Therefore, we help address the open problem on agnosticQ-learning proposed in [Wen and Van Roy,2013].
Neural Information Processing Systems
Feb-11-2026, 06:16:25 GMT
- Country:
- Technology: