Yuangang Li

Dec 5, 2024 | arxiv.org | Yuangang Li

Jun 17, 2024 | mdpi.com | Yuangang Li |Yuhan Zhang |Yunlong Gao |Bo Xu

All articles published by MDPI are made immediately available worldwide under an open access license. No specialpermission is required to reuse all or part of the article published by MDPI, including figures and tables. Forarticles published under an open access Creative Common CC BY license, any part of the article may be reused withoutpermission provided that the original article is clearly cited. For more information, please refer tohttps://www.mdpi.com/openaccess.

Aug 18, 2023 | mdpi.com | Yuangang Li |Tao Guo |Qinghua Li |Xinyue Liu

4.2. E2S2RND Algorithm Performance ExperimentWe conducted comparative experiments in the Montezuma’s Revenge experimental environment, mainly comparing the performance of E2S2RND and the original RND method, and the experimental results are shown in Figure 6. As can be seen from the figure, our proposed ESSRND method (green) and the auxiliary agent training framework E2S2RND (orange) have a significant performance improvement compared to the original RND method (red).