Cognitive Research (United States)

Imagine to Ensure Safety in Hierarchical Reinforcement Learning

This work investigates the safe exploration problem in reinforcement learning, where an agent must maximize cumulative performance while simultaneously satisfying safety constraints. This challenge becomes particularly difficult in long-horizon tasks because safe reinforcement le...

Structural analysis of the signless Brouwer conjecture: projection thresholds, extremal families, and the Laplacian–signless gap

We study the signless Brouwer conjecture (Ashraf–Omidi–Tayfeh-Rezaie): the inequality S_k(Q) ≤ m + C(k+1,2) for the sum of the k largest eigenvalues of the signless Laplacian Q = D + A of a graph with m edges, where C(k+1,2) denotes the binomial coefficient (k+1)(k)/2. We develop...