AI planning research typically assumes that complete action models are given. On the other hand, popular approaches in reinforcement learning such as Q-learning completely eschew models and planning. Neither of these approaches is satisfactory to achieve robust human-level AI that includes planning and learning in rich structured domains. In this paper, we introduce the idea of planning with pa...

Abstract: This paper designs an incentive contract menu to achieve long-term stability for electricity prices in a day-ahead electricity market. A bi-level Stackelberg game model is proposed to search for the optimal incentive mechanism under a one-leader and multi-followers gaming framework. A multi-agent simulation platform was developed to investigate the effectiveness of the incentive mecha...

Q-learning is a simple, powerful algorithm for behavior learning. It was derived in the context of single agent decision making in Markov decision process environments, but its applicability is much broader— in experiments in multiagent environments, Q-learning has also performed well. Our preliminary analysis finds that Q-learning’s indirect control of behavior via estimates of value contribut...

In a multi-agent system, action selection is important for the cooperation and coordination among agents. As the environment is dynamic and complex, modular Q-learning, which is one of the reinforcement learning schemes, is employed in assigning a proper action to an agent in the multi-agent system. The architecture of modular Q-learning consists of learning modules and a mediator module. The m...

In the paper the main analytical models of the switched reluctance (SR) machine are presented, based on geometry data, magnetic equivalent circuits and finite element (FEM) analysis results. In each case a representative example is given and finally the advantages and the weak points of each type of model are evinced.

We present a conceptual framework for creating Qlearning-based algorithms that converge to optimal equilibria in cooperative multiagent settings. This framework includes a set of conditions that are sufficient to guarantee optimal system performance. We demonstrate the efficacy of the framework by using it to analyze several well-known multi-agent learning algorithms and conclude by employing i...

The performance of off-policy learning, including deep Q-learning and deep deterministic policy gradient (DDPG), critically depends on the choice of the exploration policy. Existing exploration methods are mostly based on adding noise to the on-going actor policy and can only explore local regions close to what the actor policy dictates. In this work, we develop a simple meta-policy gradient al...

The current theoretical development identified as the gravitational decoupling via Complete Geometric Deformation (CGD) method that has been introduced to explore nonmetricity $Q$ effects in relativistic astrophysics. In present work, we have investigated gravitationally decoupled anisotropic solutions for strange star framework of $f(Q)$ gravity by utilizing CGD technique. To do this, started ...