A framework for autonomic, ontology-based IT management

The growing complexity and heterogeneity of mod- ern IT systems demand for intelligent management tools, capable of horizontally integrating technologies of different vendors and domains and vertically relating them with business processes and high level requirements. Due to their often hard-coded and unextendable management models, existing tools are not able to meet those requirements well.…

Read More

Giraffe: Using deep reinforcement learning to play chess

This report presents Giraffe, a chess engine that uses self-play to discover all its domain-specific knowledge, with minimal hand-crafted knowledge given by the programmer. Unlike previous attempts using machine learning only to perform parameter- tuning on hand-crafted evaluation functions,Giraffe’s learning system also performs automatic feature extraction and pattern recognition. The trained evaluation function performs comparably…

Read More

Human-level control through deep reinforcement learning

The theory of reinforcement learning provides a normative account1, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment…

Read More