Timezone: »
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.
Author Information
Christoph Dann (Carnegie Mellon University)
Tor Lattimore (DeepMind)
Emma Brunskill (Stanford University)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Spotlight: Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning »
Thu Dec 7th 01:10 -- 01:15 AM Room Hall A
More from the Same Authors
-
2020 Poster: Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding »
Hongseok Namkoong · Ramtin Keramati · Steve Yadlowsky · Emma Brunskill -
2020 Poster: Reinforcement Learning with Feedback Graphs »
Christoph Dann · Yishay Mansour · Mehryar Mohri · Ayush Sekhari · Karthik Sridharan -
2020 Poster: Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration »
Andrea Zanette · Alessandro Lazaric · Mykel J Kochenderfer · Emma Brunskill -
2020 Poster: Provably Good Batch Reinforcement Learning Without Great Exploration »
Yao Liu · Adith Swaminathan · Alekh Agarwal · Emma Brunskill -
2019 Poster: Offline Contextual Bandits with High Probability Fairness Guarantees »
Blossom Metevier · Stephen Giguere · Sarah Brockman · Ari Kobren · Yuriy Brun · Emma Brunskill · Philip Thomas -
2019 Poster: Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model »
Andrea Zanette · Mykel J Kochenderfer · Emma Brunskill -
2019 Poster: Limiting Extrapolation in Linear Approximate Value Iteration »
Andrea Zanette · Alessandro Lazaric · Mykel J Kochenderfer · Emma Brunskill -
2018 Poster: TopRank: A practical algorithm for online stochastic ranking »
Tor Lattimore · Branislav Kveton · Shuai Li · Csaba Szepesvari -
2018 Poster: Representation Balancing MDPs for Off-policy Policy Evaluation »
Yao Liu · Omer Gottesman · Aniruddh Raghu · Matthieu Komorowski · Aldo Faisal · Finale Doshi-Velez · Emma Brunskill -
2018 Poster: Single-Agent Policy Tree Search With Guarantees »
Laurent Orseau · Levi Lelis · Tor Lattimore · Theophane Weber -
2018 Poster: On Oracle-Efficient PAC RL with Rich Observations »
Christoph Dann · Nan Jiang · Akshay Krishnamurthy · Alekh Agarwal · John Langford · Robert Schapire -
2018 Demonstration: Automatic Curriculum Generation Applied to Teaching Novices a Short Bach Piano Segment »
Emma Brunskill · Tong Mu · Karan Goel · Jonathan Bragg -
2018 Spotlight: On Oracle-Efficient PAC RL with Rich Observations »
Christoph Dann · Nan Jiang · Akshay Krishnamurthy · Alekh Agarwal · John Langford · Robert Schapire -
2017 Poster: A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis »
Tor Lattimore -
2017 Poster: Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation »
Zhaohan Guo · Philip S. Thomas · Emma Brunskill -
2017 Tutorial: Reinforcement Learning with People »
Emma Brunskill -
2016 Poster: (Withdrawn)Only H is left: Near-tight Episodic PAC RL »
Christoph Dann · Emma Brunskill -
2016 Poster: Refined Lower Bounds for Adversarial Bandits »
Sébastien Gerchinovitz · Tor Lattimore -
2016 Poster: Causal Bandits: Learning Good Interventions via Causal Inference »
Finnian Lattimore · Tor Lattimore · Mark Reid -
2016 Poster: Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities »
Ruitong Huang · Tor Lattimore · András György · Csaba Szepesvari -
2016 Poster: On Explore-Then-Commit strategies »
Aurélien Garivier · Tor Lattimore · Emilie Kaufmann -
2015 Poster: The Pareto Regret Frontier for Bandits »
Tor Lattimore -
2015 Poster: Linear Multi-Resource Allocation with Semi-Bandit Feedback »
Tor Lattimore · Yacov Crammer · Csaba Szepesvari -
2015 Poster: Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning »
Christoph Dann · Emma Brunskill -
2015 Poster: The Human Kernel »
Andrew Wilson · Christoph Dann · Chris Lucas · Eric Xing -
2015 Spotlight: The Human Kernel »
Andrew Wilson · Christoph Dann · Chris Lucas · Eric Xing -
2014 Poster: Bounded Regret for Finite-Armed Structured Bandits »
Tor Lattimore · Remi Munos