Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning

Christoph Dann, Tor Lattimore, Emma Brunskill

Neural Information Processing Systems 

Tor Lattimore is now at DeepMind, London 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA. Uniform-P AC algorithms suffer none of these drawbacks.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found