Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....
This paper focuses on using beam search, a heuristic search algorithm, for pruning state spaces while generating. The original beam search is adapted to the state space generation ...
Abstract Hume is a domain-specific programming language targeting resourcebounded computations. It is based on generalised concurrent bounded automata, controlled by transitions c...
The difficulty of managing variations and their potential interactions across an entire product line currently hinders safety analysis in safety-critical, software product lines. ...
We propose a three-state series neural network for effective propagation of context and uncertainty information for image parsing. The activation functions used in the proposed mod...
Seyed Mojtaba Seyedhosseini Tarzjani, Antonio Paiv...