TY - GEN
T1 - Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration
AU - Agrawal, Priyank
AU - Chen, Jinglin
AU - Jiang, Nan
N1 - Publisher Copyright:
Copyright © 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved
PY - 2021
Y1 - 2021
N2 - This paper studies regret minimization with randomized value functions in reinforcement learning. In tabular finite-horizon Markov Decision Processes, we introduce a clipping variant of one classical Thompson Sampling (TS)-like algorithm, randomized least-squares value iteration (RLSVI). Our Õ(H2S√AT) high-probability worst-case regret bound improves the previous sharpest worst-case regret bounds for RLSVI and matches the existing state-of-the-art worst-case TS-based regret bounds.
AB - This paper studies regret minimization with randomized value functions in reinforcement learning. In tabular finite-horizon Markov Decision Processes, we introduce a clipping variant of one classical Thompson Sampling (TS)-like algorithm, randomized least-squares value iteration (RLSVI). Our Õ(H2S√AT) high-probability worst-case regret bound improves the previous sharpest worst-case regret bounds for RLSVI and matches the existing state-of-the-art worst-case TS-based regret bounds.
UR - http://www.scopus.com/inward/record.url?scp=85125030219&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125030219&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85125030219
T3 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
SP - 6566
EP - 6573
BT - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
PB - Association for the Advancement of Artificial Intelligence
T2 - 35th AAAI Conference on Artificial Intelligence, AAAI 2021
Y2 - 2 February 2021 through 9 February 2021
ER -