all AI news
Model approximation in MDPs with unbounded per-step cost
Feb. 15, 2024, 5:42 a.m. | Berk Bozkurt, Aditya Mahajan, Ashutosh Nayyar, Yi Ouyang
cs.LG updates on arXiv.org arxiv.org
Abstract: We consider the problem of designing a control policy for an infinite-horizon discounted cost Markov decision process $\mathcal{M}$ when we only have access to an approximate model $\hat{\mathcal{M}}$. How well does an optimal policy $\hat{\pi}^{\star}$ of the approximate model perform when used in the original model $\mathcal{M}$? We answer this question by bounding a weighted norm of the difference between the value function of $\hat{\pi}^\star $ when used in $\mathcal{M}$ and the optimal value function …
abstract approximation arxiv control cost cs.lg cs.sy decision designing eess.sy horizon markov math.oc per policy process star type
More from arxiv.org / cs.LG updates on arXiv.org
Sliced Wasserstein with Random-Path Projecting Directions
2 days, 5 hours ago |
arxiv.org
Learning Extrinsic Dexterity with Parameterized Manipulation Primitives
2 days, 5 hours ago |
arxiv.org
The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
2 days, 5 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York