Benchmarking and Evaluation in Inverse Reinforcement Learning

Image credit: @feras_dayoub
Image credit: @feras_dayoub
Authors
Peter Henderson
Published
Links
Slides
Invited Talk Reproducibility Metaresearch

Abstract

Benchmarks are particularly useful for characterizing algorithms and determining their usefulness in different settings. Here I highlight the need for more standardization of performance evaluations in inverse reinforcement learning.

Date
Location
Pittsburgh, PA, USA