1

Conditional Abstraction Trees for Sample-efficient Reinforcement Learning

In many real-world problems, the learning agent needs to learn a problem’s abstractions and solution simultaneously. However, most such abstractions need to be designed and refined by hand for different problems and domains of application. This paper …

Learning Generalized Policy Automata for Relational Stochastic Shortest Path Problems

Several goal-oriented problems in the real-worldcan be naturally expressed as Stochastic ShortestPath Problems (SSPs). However, the computa-tional complexity of solving SSPs makes findingsolutions to even moderately sized …

Differential Assessment of Black-Box AI Agents

Much of the research on learning symbolic models of AIagents focuses on agents with stationary models. This as-sumption fails to hold in settings where the agent’s capa-bilities may change as a result of learning, …

Physics-based Detection and Identification of Intergalactic clouds using Probabilistic Programming

In this talk, I present a poster on my collaborative interdisciplinary research on using first-order probabilistic logic for inferring properties of intergalactic space.

Content-based auto-tagging of audios using deep learning

In the recent years, deep learning and feature learning have drawn significant attention in the field of Music Information Retrieval (MIR) research, inspired by good results in speech recognition and computer vision. Here, we tackle the problem of …