all AI news
Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error. (arXiv:2201.12417v2 [cs.LG] UPDATED)
June 30, 2022, 1:11 a.m. | Scott Fujimoto, David Meger, Doina Precup, Ofir Nachum, Shixiang Shane Gu
stat.ML updates on arXiv.org arxiv.org
In this work, we study the use of the Bellman equation as a surrogate
objective for value prediction accuracy. While the Bellman equation is uniquely
solved by the true value function over all state-action pairs, we find that the
Bellman error (the difference between both sides of the equation) is a poor
proxy for the accuracy of the value function. In particular, we show that (1)
due to cancellations from both sides of the Bellman equation, the magnitude of
the …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Enterprise AI Architect
@ Oracle | Broomfield, CO, United States
Cloud Data Engineer France H/F (CDI - Confirmé)
@ Talan | Nantes, France