Frederik's repositories
indirect-response
Implementation of "Interpreting Indirect Answers Using Self-Rationalizing Models," a project conducted as part of the Computational Dialogue Modelling course at the University of Amsterdam.
Language:Jupyter Notebook000
google-research
Google Research
Language:Jupyter NotebookApache-2.0000
LAS-NL-Explanations
Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"
Language:PythonMIT000
Language:Python000
safety-gym
Tools for accelerating safe exploration research.
Language:PythonMIT000
Language:PythonNOASSERTION000
SPACE
Official PyTorch implementation of "SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition"
Language:PythonGPL-3.0000
tonic
Tonic RL library
Language:PythonMIT000
UvA_Summaries
Summaries of courses in the AI Master programme at UvA
Language:TeX000