scholar.google.com › citations
Apr 24, 2019 · The agent selects the most informative samples using an optimization method. This way, the initial sample is more informative than in random and ...
The agent selects the most informative samples using an optimization method. This way, the initial sample is more informative than in random and fixed strategy.
ABSTRACT A high required number of interactions with the environment is one of the most important problems in reinforcement learning.
Model-based reinforcement learning algorithms with probabilistic dynamical models are amongst the most data-efficient learning methods. This is often.
May 25, 2024 · Sample efficiency in Reinforcement Learning (RL) has traditionally been driven by algorithmic enhancements. In this work, we demonstrate that ...
Sep 21, 2023 · The paper considers a new notion of diversity in offline RL, and shows the efficiency of regularization optimization and posterior sampling ...
Model-based reinforcement learning algorithms with probabilistic dynamical models are amongst the most data-efficient learning methods. This is often.
Oct 22, 2021 · Improving the sample efficiency of reinforcement learning algorithms requires effective exploration. Following the principle of \textit{optimism ...
Abstract. This paper derives sample complexity results for using Gaussian Processes (GPs) in both model- based and model-free reinforcement learning.
To attain optimistic value function estimation without resorting to a UCB-style bonus, we introduce a reward sampling procedure that guarantees optimism in the ...