scholar.google.com › citations
Dec 22, 2022 · This paper introduces the hedonistic expected value (HEV), an upper bound of the return's expectation to quantify the uncertainty.
Dec 22, 2022 · This paper introduces the hedonistic expected value (HEV), an upper bound of the return's expectation to quantify the uncertainty.
Dec 22, 2022 · AbstractIn online reinforcement learning, operators predict the return by weighting the successors' estimated value.
TL;DR: In this paper , an uncertainty quantification based Q-learning algorithm was proposed to increase the probability of outputting an optimal partial ...
Uncertainty quantification for operators in online reinforcement learning. https://doi.org/10.1016/j.knosys.2022.109998 ·. Видання: Knowledge-Based Systems ...
We investigate statistical uncertainty quantification for reinforcement learning (RL) and its implications in exploration policy.
Mar 2, 2023 · We investigate statistical uncertainty quantification for reinforcement learning (RL) and its implications in exploration policy.
Missing: operators | Show results with:operators
We develop a sample-based approach to estimate the unknown uncertainty set, and design robust Q-learning algorithm (tabular case) and robust TDC algorithm ( ...
In this paper, we assert the importance of uncertainty quantification for machine learning and sketch an initial research agenda. We define uncertainty in the ...
Building uncertainty aware agents is impor- tant for building robust and versatile agents. The task of quantifying and incorporating uncertainty in neural ...
Missing: operators | Show results with:operators