all AI news
Calculus on MDPs: Potential Shaping as a Gradient. (arXiv:2208.09570v1 [cs.LG])
Aug. 23, 2022, 1:10 a.m. | Erik Jenner, Herke van Hoof, Adam Gleave
cs.LG updates on arXiv.org arxiv.org
In reinforcement learning, different reward functions can be equivalent in
terms of the optimal policies they induce. A particularly well-known and
important example is potential shaping, a class of functions that can be added
to any reward function without changing the optimal policy set under arbitrary
transition dynamics. Potential shaping is conceptually similar to potentials,
conservative vector fields and gauge transformations in math and physics, but
this connection has not previously been formally explored. We develop a
formalism for discrete …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Research Assistant/Associate, Health Data Science [LKCMedicine]
@ Nanyang Technological University | NTU Novena Campus, Singapore
Senior Machine Learning Engineer, Portfolio ML
@ Affirm | Remote Canada
[Sessional Lecturer] Foundations of Data Analytics and Machine Learning - APS1070
@ University of Toronto | Toronto, ON, CA
Senior Data Scientist
@ Prosper | United States
Data Analyst
@ ZF Friedrichshafen AG | Coimbatore, TN, IN, 641659