Lachine Mearning. Borotics. Irtificial Antelligence.
Applied Scientist at Amazon Research
PhD in Computer Science (Robotics / Machine Learning)
Before starting my position at Amazon, I graduated from the Robotics & Biology Lab, TU Berlin. My research activities span a variety of topics in the area of artificial intelligence, ranging from robotics, computer vision and artificial language evolution to reinforcement, unsupervised and semi-supervised learning. Before my time in academia, I co-founded and worked for several internet start-ups in Berlin.
10/05/2018: Good things come to those who wait: the extended journal version of our Amazon Picking Challenge paper has been published in Autonomous Robots.
14/10/2017: Our paper on Opening a Lockbox through Physical Exploration got accepted at Humanoids!
20/08/2017: I'm officially a PhD now! You can find my thesis here: On Decomposability in Robot Reinforcement Learning.
An excerpt of the projects that I completed in the last years.
In my thesis, I studied two problems in robot learning, ball catching and learning manipulate articulated object, and I developed a conceptual framework for understanding solutions to these problems: the spectrum of decomposability.
Research paper on learning state representations in multi-task reinforcement learning.
The paper has been presented at the NIPS Workshop on Deep Learning for Action and Interaction. The spotlight talk is online on youtube.
My blog on teaching machine learning and artificial intelligence without formal math.
Research paper on coupled learning of relational forward models and action parameters, presented at IROS 2016.
In May 2015, our Team RBO won a prestigious international robotics challenge.
The lessons learned paper won the Best Systems Paper award at RSS 2016; the paper on the perception system got nominated for Best Paper Award at IROS 2016 (see here for extended journal version).
Lightweight ML framework for learning with side information (aka privileged information), based on Theano and Lasagne; also see our paper Patterns for Learning with Side Information.
