English
Related papers

Related papers: Refined Policy Improvement Bounds for MDPs

200 papers

Recently, Large Language Models (LLMs) have rapidly evolved, approaching Artificial General Intelligence (AGI) while benefiting from large-scale reinforcement learning to enhance Human Alignment (HA) and Reasoning. Recent reward-based…

Machine Learning · Computer Science 2025-06-19 Xuerui Su , Shufang Xie , Guoqing Liu , Yingce Xia , Renqian Luo , Peiran Jin , Zhiming Ma , Yue Wang , Zun Wang , Yuting Liu

Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), as the widely employed policy based reinforcement learning (RL) methods, are prone to converge to a sub-optimal solution as they limit the policy representation…

Machine Learning · Computer Science 2020-06-16 Jun Song , Chaoyue Zhao

This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…

Machine Learning · Computer Science 2020-08-26 Lingwei Zhu , Takamitsu Matsubara

Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms. Yet, so far, such methods have been mostly analyzed from an optimization perspective, without addressing the problem of…

Machine Learning · Computer Science 2020-06-19 Yonathan Efroni , Lior Shani , Aviv Rosenberg , Shie Mannor

In reinforcement learning, the discount factor $\gamma$ controls the agent's effective planning horizon. Traditionally, this parameter was considered part of the MDP; however, as deep reinforcement learning algorithms tend to become…

Machine Learning · Computer Science 2020-06-24 Chen Tessler , Shie Mannor

Model-free reinforcement learning algorithms have seen remarkable progress, but key challenges remain. Trust Region Policy Optimization (TRPO) is known for ensuring monotonic policy improvement through conservative updates within a trust…

Machine Learning · Computer Science 2025-07-29 Zhengpeng Xie , Qiang Zhang , Fan Yang , Marco Hutter , Renjing Xu

Policy Optimization (PO) is one of the most popular methods in Reinforcement Learning (RL). Thus, theoretical guarantees for PO algorithms have become especially important to the RL community. In this paper, we study PO in adversarial MDPs…

Machine Learning · Computer Science 2023-05-16 Tal Lancewicki , Aviv Rosenberg , Dmitry Sotnikov

Reinforcement Learning (RL) agents can solve diverse tasks but often exhibit unsafe behavior. Constrained Markov Decision Processes (CMDPs) address this by enforcing safety constraints, yet existing methods either sacrifice reward…

Machine Learning · Computer Science 2025-08-18 Nikola Milosevic , Johannes Müller , Nico Scherf

Modern policy gradient algorithms, such as TRPO and PPO, outperform vanilla policy gradient in many RL tasks. Questioning the common belief that enforcing approximate trust regions leads to steady policy improvement in practice, we show…

Machine Learning · Computer Science 2025-05-27 Tao Wang , Ruipeng Zhang , Sicun Gao

Motivated by applications in risk-sensitive reinforcement learning, we study mean-variance optimization in a discounted reward Markov Decision Process (MDP). Specifically, we analyze a Temporal Difference (TD) learning algorithm with linear…

Machine Learning · Computer Science 2025-03-13 Tejaram Sangadi , L. A. Prashanth , Krishna Jagannathan

Traditional policy gradient methods are fundamentally flawed. Natural gradients converge quicker and better, forming the foundation of contemporary Reinforcement Learning such as Trust Region Policy Optimization (TRPO) and Proximal Policy…

Machine Learning · Computer Science 2022-09-07 W. J. A. van Heeswijk

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the…

Machine Learning · Computer Science 2025-03-19 Shuyu Yin , Fei Wen , Peilin Liu , Tao Luo

We study upper and lower bounds on the sample-complexity of learning near-optimal behaviour in finite-state discounted Markov Decision Processes (MDPs). For the upper bound we make the assumption that each action leads to at most two…

Machine Learning · Computer Science 2013-05-17 Tor Lattimore , Marcus Hutter

In this paper, we study a mean-variance optimization problem in an infinite horizon discrete time discounted Markov decision process (MDP). The objective is to minimize the variance of system rewards with the constraint of mean performance.…

Optimization and Control · Mathematics 2017-08-24 Li Xia

We study the policy testing problem in discounted Markov decision processes (MDPs) in the fixed-confidence setting under a generative model with static sampling. The goal is to decide whether the value of a given policy exceeds a specified…

Machine Learning · Statistics 2026-04-21 Kaito Ariu , Po-An Wang , Alexandre Proutiere , Kenshi Abe

Much of the recent success of deep reinforcement learning has been driven by regularized policy optimization (RPO) algorithms with strong performance across multiple domains. In this family of methods, agents are trained to maximize…

Machine Learning · Computer Science 2022-03-24 Ted Moskovitz , Michael Arbel , Jack Parker-Holder , Aldo Pacchiano

We investigate the problem of best policy identification in discounted linear Markov Decision Processes in the fixed confidence setting under a generative model. We first derive an instance-specific lower bound on the expected number of…

Machine Learning · Computer Science 2022-08-12 Jerome Taupin , Yassir Jedra , Alexandre Proutiere

Trust Region Policy Optimization (TRPO) is a popular and empirically successful policy search algorithm in reinforcement learning (RL). It iteratively solved the surrogate problem which restricts consecutive policies to be close to each…

Machine Learning · Computer Science 2021-10-27 Sahar Roostaie , Mohammad Mehdi Ebadzadeh

We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. Compared to prior work, our bounds depend on alternative definitions of gaps. These definitions are based on the…

Machine Learning · Computer Science 2021-10-27 Christoph Dann , Teodor V. Marinov , Mehryar Mohri , Julian Zimmert

In this work, we provide theoretical guarantees for reward decomposition in deterministic MDPs. Reward decomposition is a special case of Hierarchical Reinforcement Learning, that allows one to learn many policies in parallel and combine…

Machine Learning · Computer Science 2018-03-14 Tom Zahavy , Avinatan Hasidim , Haim Kaplan , Yishay Mansour