The development of efficient methods for the removal of organic dyes, which are considered to be toxic to the aquatic biota and therefore destroy the ecosystem, is required. In this study, the extraction of methylene blue (MB) from aqueous solution into DEHPA/isooctane solution was investigated. MB was hardly extracted at all from the aqueous to the organic phase at pH values below 5, and the extraction ratio of MB greatly increased with increasing pH in the range of 5-6 by the electrostatic attraction between dissociated DEHPA and MB. MB was not extracted to the organic phase at pH values above 6, since DEHPA leaked from the organic to the aqueous phase. The addition of 2-ethyl-1-hexanol suppressed the DEHPA leakage, and then MB was successfully extracted to the organic phase at pH values above 6. It was found that MB was solubilized as an MB-DEHPA complex in the organic phase in the pH range of 5-5.5, whereas MB would be entrapped in the waterpool of the reversed micelle at pH values above 5.5. The back extraction ratio of MB from the organic to the aqueous phase was about 100 % at pH values below 5 because of the destruction of the reversed micelles and the disappearance of the electrostatic attraction between DEHPA and MB.
Randomized ensemble double Q-learning (REDQ) (Chen et al., 2021b) has recently achieved state-of-the-art sample efficiency on continuous-action reinforcement learning benchmarks. This superior sample efficiency is possible by using a large Q-function ensemble. However, REDQ is much less computationally efficient than non-ensemble counterparts such as Soft Actor-Critic (SAC) (Haarnoja et al., 2018a). To make REDQ more computationally efficient, we propose a method of improving computational efficiency called Dr.Q, which is a variant of REDQ that uses a small ensemble of dropout Q-functions. Our dropout Q-functions are simple Q-functions equipped with dropout connection and layer normalization. Despite its simplicity of implementation, our experimental results indicate that Dr.Q is doubly (sample and computationally) efficient. It achieved comparable sample efficiency with REDQ and much better computational efficiency than REDQ and comparable computational efficiency with that of SAC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.