This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
Hierarchical state decompositions address the curse-ofdimensionality in Q-learning methods for reinforcement learning (RL) but can suffer from suboptimality. In addressing this, w...
Erik G. Schultink, Ruggiero Cavallo, David C. Park...
We propose, and justify, an economic theory to guide memory system design, operation, and analysis. Our theory treats memory random-access latency, and its cost per installed mega...
Blackouts in our daily life can be disastrous with enormous economic loss. Blackouts usually occur when appropriate corrective actions are not effectively taken for an initial con...
Ming Chen, Clinton Nolan, Xiaorui Wang, Sarina Adh...
Hierarchies are one of the most common organizational structures observed in multi-agent systems. In this paper we study vertical specialization as a reason for hierarchical struc...