This paper introduces a principled approach for the design of a scalable general reinforcement learning agent. This approach is based on a direct approximation of AIXI, a Bayesian...
Joel Veness, Kee Siong Ng, Marcus Hutter, David Si...
In this paper, a grey neuro-adaptive control algorithm is suggested for Antilock Braking Systems (ABS). The concept of grey system theory, which has a certain prediction capabilit...
Erdal Kayacan, Yesim Oniz, Okyay Kaynak, Andon V. ...
The last decade of basic research in the area of Description Logics (DL) has created a stable theory, efficient inference procedures, and has demonstrated a wide applicability of ...
We study algorithmic questions concerning a basic microeconomic congestion game in which there is a single provider that offers a service to a set of potential customers. Each cus...
Adaptive neural network is a powerful tool for prediction of air pollution abatement scenarios. But it is often difficult to avoid overfit during the training of adaptive neural n...