Research
Optimizing over a Restricted Policy Class in MDPs
April 15, 2019
Abstract
We address the problem of finding an optimal policy in a Markov decision process under a restricted policy class defined by the convex hull of a set of base policies. This problem is of great interest in applications in which a number of reasonably good (or safe) policies are already known and we are interested in optimizing in their convex hull. We first prove that solving this problem is NP-hard. We then propose an efficient algorithm that finds a policy whose performance is almost as good as that of the best convex combination of the base policies, under the assumption that the occupancy measures of the base policies have a large overlap. The running time of the proposed algorithm is linear in the number of states and polynomial in the number of base policies. A distinct advantage of the proposed algorithm is that, apart from the computation of the occupancy measures of the base policies, it does not need to interact with the environment during the optimization process. This is especially important (i) in problems that due to concerns such as safety, we are restricted in interacting with the environment only through the (safe) base policies, and (ii) in complex systems where estimating the value of a policy can be a time consuming process.
AUTHORS
Publisher
Related Publications
February 11, 2026
Computer Vision
UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
Leon Liangyu Chen, Haoyu Ma, Zhipeng Fan, Ziqi Huang, Animesh Sinha, Xiaoliang Dai, Jialiang Wang, Zecheng He, Jianwei Yang, Chunyuan Li, Junzhe Sun, Chu Wang, Serena Yeung-Levy, Felix Juefei-Xu
February 11, 2026
December 18, 2025
Computer Vision
Pixel Seal: Adversarial-only training for invisible image and video watermarking
Tomáš Souček, Pierre Fernandez, Hady Elsahar, Sylvestre Rebuffi, Valeriu Lacatusu, Tuan Tran, Tom Sander, Alexandre Mourachko
December 18, 2025
November 19, 2025
Computer Vision
SAM 3: Segment Anything with Concepts
Nicolas Carion, Laura Gustafson, Yuan-Ting Hu, Shoubhik Debnath, Ronghang Hu, Didac Suris Coll-Vinent, Chaitanya Ryali, Kalyan Vasudev Alwala, Haitham Khedr, Andrew Huang, Jie Lei, Tengyu Ma, Baishan Guo, Arpit Kalla, Markus Marks, Joseph Greer, Meng Wang, Peize Sun, Roman Rädle, Triantafyllos Afouras, Effrosyni Mavroudi, Katherine Xu, Tsung-Han Wu, Yu Zhou, Liliane Momeni, Rishi Hazra, Shuangrui Ding, Sagar Vaze, Francois Porcher, Feng Li, Siyuan Li, Aishwarya Kamath, Ho Kei Cheng, Piotr Dollar, Nikhila Ravi, Kate Saenko, Pengchuan Zhang, Christoph Feichtenhofer
November 19, 2025
November 18, 2025
Core Machine Learning
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
Shalini Maiti *, Amar Budhiraja *, Bhavul Gauri, Gaurav Chaurasia, Anton Protopopov, Alexis Audran-Reiss, Michael Slater, Despoina Magka, Tatiana Shavrina, Roberta Raileanu, Yoram Bachrach, * Equal authorship
November 18, 2025
October 31, 2019
NLP
Facebook AI's WAT19 Myanmar-English Translation Task Submission
Peng-Jen Chen, Jiajun Shen, Matt Le, Vishrav Chaudhary, Ahmed El-Kishky, Guillaume Wenzek, Myle Ott, Marc’Aurelio Ranzato
October 31, 2019
October 27, 2019
Order-Aware Generative Modeling Using the 3D-Craft Dataset | Facebook AI Research
Zhuoyuan Chen, Demi Guo, Tong Xiao, Saining Xie, Xinlei Chen, Haonan Yu, Jonathan Gray, Kavya Srinet, Haoqi Fan, Jerry Ma, Charles R. Qi, Shubham Tulsiani, Arthur Szlam, Larry Zitnick
October 27, 2019
April 25, 2020
Energy-Based Models for Atomic-Resolution Protein Conformations | Facebook AI Research
Yilun Du, Joshua Meier, Jerry Ma, Rob Fergus, Alexander Rives
April 25, 2020
June 11, 2019
Computer Vision
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero | Facebook AI Research
Yuandong Tian, Jerry Ma, Qucheng Gong, Shubho Sengupta, Zhuoyuan Chen, James Pinkerton, Larry Zitnick
June 11, 2019
Help Us Pioneer The Future of AI
We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.
Our approach
Latest news
Foundational models
Meta © 2026