Reward Biased Maximum Likelihood Estimation for Learning in Constrained MDPs

We use the Reward Biased Maximum Likelihood Estimation (RBMLE) algorithm to learn optimal policies for constrained Markov Decision Processes (CMDPs). We analyze the learning regrets of RBMLE.

Reinforcement Learning in Robotics Machine Learning and Algorithms Data Stream Mining Techniques

Paper

Similar papers

Reward Biased Maximum Likelihood Estimation for Reinforcement LearningAkshay Mete, Rahul Singh, Xi Liu et al.2020 · Conference on Learning for Dynamics & Control · 25 citations In Library

The RBMLE method for Reinforcement LearningAkshay Mete, Rahul Singh, P. Kumar2022 · Annual Conference on Information Sciences and Systems · 3 citations In Library

Value-Biased Maximum Likelihood Estimation for Model-based Reinforcement Learning in Discounted Linear MDPsYu-Heng Hung, Ping-Chun Hsieh, Akshay Mete et al.2023 · arXiv (Cornell University) · 2 citations In Library

Reward-Biased Maximum Likelihood Estimation for Neural Contextual BanditsYu-Heng Hung, Ping-Chun Hsieh2022 · AAAI Conference on Artificial Intelligence · 2 citations In Library

The Reward Biased Method: An Optimism based Approach for Reinforcement LearningAkshay Mete, Rahul Singh, P. R. Kumar2023 · Allerton Conference on Communication, Control, and Computing · 1 citation In Library

IMED-RL: Regret optimal learning of ergodic Markov decision processesFabien Pesquerel, Odalric-Ambrym Maillard2022 · Neural Information Processing Systems · 11 citations In Library

IMED-RL:Regret optimal learning of ergodic Markov decision processesFabien Pesquerel, Odalric-Ambrym Maillard2022 · HAL (Le Centre pour la Communication Scientifique Directe) In Library

Model-Based Reinforcement Learning for Infinite-Horizon Discounted Constrained Markov Decision ProcessesAria HasanzadeZonuzy, Dileep Kalathil, Srinivas Shakkottai2021 · International Joint Conference on Artificial Intelligence · 12 citations In Library

A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision ProcessesHonghao Wei, Xin Liu, Lei Ying2022 · Proceedings of the AAAI Conference on Artificial Intelligence · 35 citations In Library

Reward-Biased Maximum Likelihood Estimation for Linear Stochastic BanditsYu-Heng Hung, Ping-Chun Hsieh, Xi Liu et al.2020 · AAAI Conference on Artificial Intelligence · 17 citations In Library

Source of record

OpenAlex

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal