Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning
Christoph Dann, Tor Lattimore, Emma Brunskill
–Neural Information Processing Systems
Statistical performance bounds for reinforcement learning (RL) algorithms can be critical for high-stakes applications like healthcare. This paper introduces a new framework for theoretically measuring the performance of such algorithms called Uniform-PAC, which is a strengthening of the classical Probably Approximately Correct (PAC) framework. In contrast to the PAC framework, the uniform version may be used to derive high probability regret guarantees and so forms a bridge between the two setups that has been missing in the literature. We demonstrate the benefits of the new framework for finite-state episodic MDPs with a new algorithm that is Uniform-PAC and simultaneously achieves optimal regret and PAC guarantees except for a factor of the horizon.
Neural Information Processing Systems
Oct-7-2024, 14:25:47 GMT
- Country:
- Europe > United Kingdom
- England (0.14)
- North America > United States
- California (0.14)
- Europe > United Kingdom
- Industry:
- Health & Medicine (0.88)