← Search

Jaime Fisac

2 accepted papers

2018

An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning

ICML 2018oral

Our goal is for AI systems to correctly identify and act according to their human user’s objectives. Cooperative Inverse Reinforcement Learning (CIRL) formalizes this value alignment problem as a two-player game between a human and robot, in which only the human knows the parameters of the reward fu…

Cited by 45SourcePDFScholar
2018

Probabilistically Safe Robot Planning with Confidence-Based Human Predictions

RSS 2018poster

In order to safely operate around humans, robots can employ predictive models of human motion. Unfortunately, these models cannot capture the full complexity of human behavior and necessarily introduce simplifying assumptions. As a result, predictions may degrade whenever the observed human behavior…

Cited by 169SourcePDFScholar