Autonomous AI systems will be entering human society in the near future to provide services and work alongside humans. For those systems to be accepted and trusted, the users should be able to understand the reasoning process of the system, i.e. the system should be transparent. System transparency enables humans to form coherent explanations of the systems decisions and actions. Transparency is important not only for user trust, but also for software debugging and certification. In recent years, Deep Neural Networks have made great advances in multiple application areas. However, deep neural networks are opaque. In this paper, we report on work in transparency in Deep Reinforcement Learning Networks (DRLN). Such networks have been extremely successful in accurately learning action control in image input domains, such as Atari games. In this paper, we propose a novel and general method that (a) incorporates explicit object recognition processing into deep reinforcement learning models, (b) forms the basis for the development of object saliency maps, to provide visualization of internal states of DRLNs, thus enabling the formation of explanations and (c) can be incorporated in any existing deep reinforcement learning framework. We present computational results and human experiments to evaluate our approach.

No abstract

The heterogeneous wireless networks where coexistence of different Radio access technology (RAT) are widely deployed for various services and support various traffic demand, channel allocation. Under heterogeneous wireless networks, a user can send data through a single or multi RATs simultaneous. The objective of this paper is to choose the optimal bandwidth for the services and power allocation to that bandwidth. The proposed distributed joint allocation algorithm using modifiedNewton method is adopted to maximize the total system capacity. We validate the performance of the proposed algorithm through numerical results.

No abstract

No abstract