56 citations · 94 across the 9 of their papers we have counts for
11 papers
Q-based Variational Inverse Reinforcement Learning
Ondrej Bajgar, Peter Tisnikar, Alessandro Abate +2
The development of safe and beneficial AI requires that systems can learn and act in accordance with human preferences. However, explicitly specifying these preferences by hand is…
PAC Apprenticeship Learning with Bayesian Active Inverse Reinforcement Learning
Ondrej Bajgar, Dewi S. W. Gould, Jonathon Liu +3
As AI systems become increasingly autonomous, reliably aligning their decision-making with human preferences is essential. Inverse reinforcement learning (IRL) offers a promising a…
Toward Information Theoretic Active Inverse Reinforcement Learning
Ondrej Bajgar, Sid William Gould, Rohan Narayan Langford Mitta +3
As AI systems become increasingly autonomous, aligning their decision-making to human preferences is essential. In domains like autonomous driving or robotics, it is impossible to…
Walking the Values in Bayesian Inverse Reinforcement Learning
Ondrej Bajgar, Alessandro Abate, Konstantinos Gatsis +1
The goal of Bayesian inverse reinforcement learning (IRL) is recovering a posterior distribution over reward functions using a set of demonstrations from an expert optimizing for a…
Negative Human Rights as a Basis for Long-term AI Safety and Regulation
Ondrej Bajgar, Jan Horenovsky
If autonomous AI systems are to be reliably safe in novel situations, they will need to incorporate general principles guiding them to recognize and avoid harmful behaviours. Such…
Planning for Goal-Oriented Dialogue Systems
Christian Muise, Tathagata Chakraborti, Shubham Agarwal +6
Generating complex multi-turn goal-oriented dialogue agents is a difficult problem that has seen a considerable focus from many leaders in the tech industry, including IBM, Google,…
Generating Dialogue Agents via Automated Planning
Adi Botea, Christian Muise, Shubham Agarwal +9
Dialogue systems have many applications such as customer support or question answering. Typically they have been limited to shallow single turn interactions. However more advanced…
A Boo(n) for Evaluating Architecture Performance
Ondrej Bajgar, Rudolf Kadlec, Jan Kleindienst
We point out important problems with the common practice of using the best single model performance for comparing deep learning architectures, and we propose a method that corrects…
Knowledge Base Completion: Baselines Strike Back
Rudolf Kadlec, Ondrej Bajgar, Jan Kleindienst
Many papers have been published on the knowledge base completion task in the past few years. Most of these introduce novel architectures for relation learning that are evaluated on…
Embracing data abundance: BookTest Dataset for Reading Comprehension
Ondrej Bajgar, Rudolf Kadlec, Jan Kleindienst
There is a practically unlimited amount of natural language data available. Still, recent work in text comprehension has focused on datasets which are small relative to current com…
Text Understanding with the Attention Sum Reader Network
Rudolf Kadlec, Martin Schmid, Ondrej Bajgar +1
Several large cloze-style context-question-answer datasets have been introduced recently: the CNN and Daily Mail news data and the Children's Book Test. Thanks to the size of these…