all AI news
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses. (arXiv:2205.07704v2 [stat.ML] UPDATED)
June 23, 2022, 1:12 a.m. | Daniil Tiapkin, Denis Belomestny, Eric Moulines, Alexey Naumov, Sergey Samsonov, Yunhao Tang, Michal Valko, Pierre Menard
stat.ML updates on arXiv.org arxiv.org
We propose the Bayes-UCBVI algorithm for reinforcement learning in tabular,
stage-dependent, episodic Markov decision process: a natural extension of the
Bayes-UCB algorithm by Kaufmann et al. (2012) for multi-armed bandits. Our
method uses the quantile of a Q-value function posterior as upper confidence
bound on the optimal Q-value function. For Bayes-UCBVI, we prove a regret bound
of order $\widetilde{O}(\sqrt{H^3SAT})$ where $H$ is the length of one episode,
$S$ is the number of states, $A$ the number of actions, $T$ the …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US