This paper describes a method for hierarchical reinforcement learning in which high-level policies automatically discover subgoals, and low-level policies learn to specialize for ...
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...
When we construct an agent by integrating modules, there appear troubles concerning the autonomy of the agent if we introduce a heuristics that dominates the whole agent. Thus, we ...
Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large-scale systems. In this work, we develop a supervision fr...
Chongjie Zhang, Sherief Abdallah, Victor R. Lesser
In this paper, we show how the dynamics of Q-learning can be visualized and analyzed from a perspective of Evolutionary Dynamics (ED). More specifically, we show how ED can be use...