This paper presents postponed updates, a new strategy for TD methods that can improve sample efficiency without incurring the computational and space requirements of model-based ...
The paper explores a very simple agent design method called Q-decomposition, wherein a complex agent is built from simpler subagents. Each subagent has its own reward function and...
Recently researchers have introduced methods to develop reusable knowledge in reinforcement learning (RL). In this paper, we define simple principles to combine skills in reinforce...
Model checking by exhaustive state space enumeration is one of the most developed analysis methods for distributed event systems. Its main problem—the size of the state spaces—...
Imitation is actively being studied as an effective means of learning in multi-agent environments. It allows an agent to learn how to act well (perhaps optimally) by passively obs...