Katja Hofmann

Researcher at Microsoft Research Cambridge, UK

About

Future interactive systems will learn directly from their users, and continuously adapt to their preferences. My research goal is to develop exploration, reward, and learning approaches that will make this possible. [...]

Pages

About
Contact
Publications

Search

Search for:

Contact

Katja Hofmann

Intelligent Systems Lab Amsterdam
Informatics Institute
University of Amsterdam

Room C3.258
Science Park 904
1098 XH Amsterdam

+31 (20) 525 6767

LinkedIn
Twitter

Advertisements

Recent Posts

Query Formulation with Query Auto-Completion
RUSSIR 2014: Lectures on Online Experimentation for Information Retrieval
Fast and Reliably Online Learning to Rank for Information Retrieval
Practical Online Retrieval Evaluation
Balancing Exploration and Exploitation in Online Learning to Rank for IR

Recent Tweets

@luisa_zintgraf Congratulations!! 11 hours ago
RT @le_roux_nicolas: Thanks to everyone accepting to do emergency reviews. You rock! If I see you in Montreal, at NIPS or not, drinks are o… 1 day ago
RT @cholodovskis: In 20 minutes I'll be giving a talk at the Computer Games Workshop @IJCAI_ECAI_18 titled Revisiting the ALE: Evaluation P… 2 days ago

Follow @katjahofmann

Microsoft Research News

New perspectives on contextual bandit
What is the common denominator between the following situations: a doctor choosing among different drugs for a sequence of patients; a website selecting ads for its visitors based on the information it has about them; and a travel agency making recommendations to its customers for their next vacation? All can be viewed as instances of […] The post New perspe […]
TextWorld: A learning environment for training reinforcement learning agents, inspired by text-based games
Today, fresh out of the Microsoft Research Montreal lab, comes an open-source project called TextWorld. TextWorld is an extensible Python framework for generating text-based games. Reinforcement learning researchers can use TextWorld to train and test AI agents in skills such as language understanding, affordance extraction, memory and planning, exploration […]
Helping proteomics scientists share peptide data: Azure does the heavy lifting
Scientific research breakthroughs are often achieved when many different scientists, in different labs and organizations, work together on a single task. That happened at the turn of the 21st century with the Human Genome Project, where human DNA was mapped for future reference and is now key to many breakthroughs in medicine. This is happening […] The post […]

Recent MSR Publications

New perspectives on contextual bandit
What is the common denominator between the following situations: a doctor choosing among different drugs for a sequence of patients; a website selecting ads for its visitors based on the information it has about them; and a travel agency making recommendations to its customers for their next vacation? All can be viewed as instances of […] The post New perspe […]
TextWorld: A learning environment for training reinforcement learning agents, inspired by text-based games
Today, fresh out of the Microsoft Research Montreal lab, comes an open-source project called TextWorld. TextWorld is an extensible Python framework for generating text-based games. Reinforcement learning researchers can use TextWorld to train and test AI agents in skills such as language understanding, affordance extraction, memory and planning, exploration […]
Helping proteomics scientists share peptide data: Azure does the heavy lifting
Scientific research breakthroughs are often achieved when many different scientists, in different labs and organizations, work together on a single task. That happened at the turn of the 21st century with the Human Genome Project, where human DNA was mapped for future reference and is now key to many breakthroughs in medicine. This is happening […] The post […]

New at ILPS

An error has occurred; the feed is probably down. Try again later.

Blog at WordPress.com.

Privacy & Cookies: This site uses cookies. By continuing to use this website, you agree to their use.
To find out more, including how to control cookies, see here: Cookie Policy