מחקר עיצוב הדרגתי של מקודדים חזותיים

תקציר מקורי באנגליתarXiv:2608.07335v4 Announce Type: replace Abstract: Replay-free parallelized Q-learning removes the large experience replay buffers and target networks used by conventional deep Q-learning, but the role of network architecture in this training regime remains comparatively underexplored. We investigate this question through a progressive three-phase study within the Parallelized Q-Network (PQN) framework. First, we compare eight convolutional encoder topologies on Atari-57 under a common training protocol while jointly considering performance and computational complexity. Second, we integrate Hadamax-style multiplicative feature interactions and explicit pooling into the selected encoder hierarchy. Third, with the visual representation fixed, we compare complete categorical-dueling, ensembl