← Search

Borja Ibarz

2 accepted papers

2023

Neural Algorithmic Reasoning with Causal Regularisation

ICML 2023poster

Recent work on neural algorithmic reasoning has investigated the reasoning capabilities of neural networks, effectively demonstrating they can learn to execute classical algorithms on unseen data coming from the train distribution. However, the performance of existing neural reasoners significantly…

Cited by 30SourcePDFScholar
2018

Reward learning from human preferences and demonstrations in Atari

NeurIPS 2018poster

To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we need humans to communicate an objective to the agent directly. In this work, we combine two approaches to this problem: learning from expert demonstrations and learnin…

Cited by 504SourcePDFScholar