Han Zhang @hanzhang.bsky.social · 28/09/2026Compared to MLP and transformers, the priority-based agent trained more efficiently and handled unseen, hazardous scenarios better, even from simple demonstrations. Below is the agent handling x4 speed at ease, even without being trained on it. 100
Han Zhang @hanzhang.bsky.social · 28/09/2026We could even produce a human-like, history-driven effect, where the agent anticipates the upcoming target location: 110
Han Zhang @hanzhang.bsky.social · 28/09/2026So, incorporating principles of human cognition makes artificial systems more efficient and robust. As much of the discussion around AI focuses on scaling up, perhaps cognitive science offers another approach to building better systems? 020
