English

Reward Biased Maximum Likelihood Estimation for Learning in Constrained MDPs

Optimization and Control 2021-05-31 v1
Authors: Rahul Singh
View on arXiv ↗ PDF ↗

Abstract

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.

Keywords

markov decision processes optimization model selection

Cite

@article{arxiv.2105.13919,
  title  = {Reward Biased Maximum Likelihood Estimation for Learning in Constrained MDPs},
  author = {Rahul Singh},
  journal= {arXiv preprint arXiv:2105.13919},
  year   = {2021}
}

Comments

Under preparation. arXiv admin note: text overlap with arXiv:2011.07738

Related papers

View all related →
Machine Learning · Computer Science
Reward Biased Maximum Likelihood Estimation for Reinforcement Learning
Akshay Mete, Rahul Singh, Xi Liu, P. R. Kumar
2021-05-18
Machine Learning · Computer Science
Value-Biased Maximum Likelihood Estimation for Model-based Reinforcement Learning in Discounted Linear MDPs
Yu-Heng Hung, Ping-Chun Hsieh, Akshay Mete, P. R. Kumar
2023-10-19
Machine Learning · Computer Science
Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits
Yu-Heng Hung, Ping-Chun Hsieh
2022-05-31
Machine Learning · Computer Science
Reinforcement Learning algorithms for regret minimization in structured Markov Decision Processes
K J Prabuchandran, Tejas Bodas, Theja Tulabandhula
2016-08-18
Machine Learning · Computer Science
Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees
Sourav Ganguly, Kishan Panaganti, Arnob Ghosh, Adam Wierman
2026-02-10
Optimization and Control · Mathematics
Reinforcement Learning of Markov Decision Processes with Peak Constraints
Ather Gattami
2019-12-09
Machine Learning · Computer Science
Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty
Reazul Hasan Russel, Mouhacine Benosman, Jeroen Van Baar
2020-10-13
Machine Learning · Computer Science
Tackling Decision Processes with Non-Cumulative Objectives using Reinforcement Learning
Maximilian Nägele, Jan Olle, Thomas Fösel, Remmy Zen +1
2025-05-26
Machine Learning · Computer Science
Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits
Xi Liu, Ping-Chun Hsieh, Anirban Bhattacharya, P. R. Kumar
2020-10-26
Machine Learning · Computer Science
Online Reinforcement Learning of Optimal Threshold Policies for Markov Decision Processes
Arghyadip Roy, Vivek Borkar, Abhay Karandikar, Prasanna Chaporkar
2021-08-24
Machine Learning · Computer Science
Provably Efficient Exploration in Constrained Reinforcement Learning:Posterior Sampling Is All You Need
Danil Provodin, Pratik Gajane, Mykola Pechenizkiy, Maurits Kaptein
2023-09-28
Machine Learning · Computer Science
A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints
Jacopo Germano, Francesco Emanuele Stradi, Gianmarco Genalti, Matteo Castiglioni +2
2024-08-30
Machine Learning · Computer Science
Inverse Reinforcement Learning With Constraint Recovery
Nirjhar Das, Arpan Chattopadhyay
2024-01-08
Machine Learning · Computer Science
Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes
Yi Tian, Jian Qian, Suvrit Sra
2020-06-25
Machine Learning · Computer Science
Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints
Francesco Emanuele Stradi, Anna Lunghi, Matteo Castiglioni, Alberto Marchesi +1
2024-09-27
Machine Learning · Statistics
Variance-Adaptive Optimal Algorithm for Reinforcement Learning with Multinomial Logit Function Approximation
Wonyoung Kim, Min-Hwan Oh, Garud Iyengar, Assaf Zeevi
2026-05-28
Machine Learning · Computer Science
Reconnaissance and Planning algorithm for constrained MDP
Shin-ichi Maeda, Hayato Watahiki, Shintarou Okada, Masanori Koyama
2019-09-23
Machine Learning · Computer Science
Reward-Mixing MDPs with a Few Latent Contexts are Learnable
Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor
2022-10-07
Artificial Intelligence · Computer Science
Best-Effort Policies for Robust Markov Decision Processes
Alessandro Abate, Thom Badings, Giuseppe De Giacomo, Francesco Fabiano
2025-11-20
Machine Learning · Computer Science
Risk-sensitive Markov Decision Process and Learning under General Utility Functions
Zhengqi Wu, Renyuan Xu
2024-12-24
Artificial Intelligence · Computer Science
Risk-Constrained Reinforcement Learning with Percentile Risk Criteria
Yinlam Chow, Mohammad Ghavamzadeh, Lucas Janson, Marco Pavone
2017-04-07
Machine Learning · Computer Science
Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling
Danil Provodin, Maurits Kaptein, Mykola Pechenizkiy
2024-05-30
Machine Learning · Computer Science
Variational Regret Bounds for Reinforcement Learning
Pratik Gajane, Ronald Ortner, Peter Auer
2019-09-11
Machine Learning · Computer Science
Learning in Markov Decision Processes under Constraints
Rahul Singh, Abhishek Gupta, Ness B. Shroff
2023-03-16
Machine Learning · Computer Science
On the Performance of Maximum Likelihood Inverse Reinforcement Learning
Héctor Ratia, Luis Montesano, Ruben Martinez-Cantin
2012-02-09
R2 v1 2026-06-24T02:34:40.061Z