We explore dynamic shaping to integrate our prior beliefs of the final policy into a conventional reinforcement learning system. Shaping provides a positive or negative artificial...
Conditional random fields (CRFs) are graphical models for modeling the probability of labels given the observations. They have traditionally been trained with using a set of obser...
Xinhua Zhang, Douglas Aberdeen, S. V. N. Vishwanat...
Shaping can be an effective method for improving the learning rate in reinforcement systems. Previously, shaping has been heuristically motivated and implemented. We provide a for...
Decentralized reinforcement learning (DRL) has been applied to a number of distributed applications. However, one of the main challenges faced by DRL is its convergence. Previous ...
Chongjie Zhang, Victor R. Lesser, Sherief Abdallah
We address the problem of autonomously learning controllers for visioncapable mobile robots. We extend McCallum's (1995) Nearest-Sequence Memory algorithm to allow for genera...
Viktor Zhumatiy, Faustino J. Gomez, Marcus Hutter,...