https://sites.temple.edu/trail/files/2021/11/XieXinDamesIROS2021.pdf
destrians often bumping into one another. Future work will aim to mitigate this issue by using an experienced human expert to train our system and real pedestrians to train/test our system (once the COVID-19 pandemic subsides and it is again safe to conduct real-world
https://cis.temple.edu/~jiewu/research/publications/Publication_files/Distributed_Deep_Multi-Agent_Reinforcement_Learning_for_Cooperative_Edge_Caching_in_Internet-of-Vehicles.pdf
This situation may occur because LFU and LRU learn only from one-step past and operate based on simple rules, while RL-based edge caching methods can be derived from the observed historical content demands and concentrate more on the reward that agents can earn rather than users’ requests.
https://cis.temple.edu/~wu/research/publications/Publication_files/ICDE2024_Xu.pdf
Here, the popularity of v1 is higher than v2, and Alice (or Bob) is capable of only caching one video due to the limited storage resources. Considering that high-popularity videos can generate more trading incomes, Alice and Bob generally tend to cache v1 to improve their utilities (i.e., net profits).