English
Related papers

Related papers: Anchor-Changing Regularized Natural Policy Gradien…

200 papers

Markov decision processes (MDPs) are a popular model for performance analysis and optimization of stochastic systems. The parameters of stochastic behavior of MDPs are estimates from empirical observations of a system; their values are not…

Artificial Intelligence · Computer Science 2017-10-26 Dimitri Scheftelowitsch , Peter Buchholz , Vahid Hashemi , Holger Hermanns

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

Machine Learning · Computer Science 2026-04-01 Abhishek Gupta , Aditya Mahajan

Reinforcement learning usually assumes a given or sometimes even fixed environment in which an agent seeks an optimal policy to maximize its long-term discounted reward. In contrast, we consider agents that are not limited to passive…

Machine Learning · Computer Science 2025-10-20 Ziqing Lu , Babak Hassibi , Lifeng Lai , Weiyu Xu

Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning. There have been a flurry of recent…

Optimization and Control · Mathematics 2024-04-12 Jiacai Liu , Wenye Li , Ke Wei

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg

We propose policy gradient algorithms for robust infinite-horizon Markov decision processes (MDPs) with non-rectangular uncertainty sets, thereby addressing an open challenge in the robust MDP literature. Indeed, uncertainty sets that…

Optimization and Control · Mathematics 2025-09-30 Mengmeng Li , Daniel Kuhn , Tobias Sutter

Markov Decision Processes (MDPs) are a formal framework for modeling and solving sequential decision-making problems. In finite-time horizons such problems are relevant for instance for optimal stopping or specific supply chain problems,…

Optimization and Control · Mathematics 2024-05-07 Sara Klein , Simon Weissmann , Leif Döring

A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent…

Machine Learning · Computer Science 2019-08-22 Tiancheng Yu , Suvrit Sra

Constrained Markov Decision Process (CMDP) is a natural framework for reinforcement learning tasks with safety constraints, where agents learn a policy that maximizes the long-term reward while satisfying the constraints on the long-term…

Artificial Intelligence · Computer Science 2018-02-20 Qingkai Liang , Fanyu Que , Eytan Modiano

This thesis develops theoretical frameworks and algorithms that advance constrained reinforcement learning (RL) across control, preference learning, and alignment of large language models. The first contribution addresses constrained Markov…

Machine Learning · Computer Science 2025-12-12 Akhil Agnihotri

This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled POMDPs. We introduce GPOMDP, a REINFORCE-like algorithm for estimating an approximation to…

Machine Learning · Computer Science 2025-12-08 Jonathan Baxter , Peter L. Bartlett

A tenet of reinforcement learning is that the agent always observes rewards. However, this is not true in many realistic settings, e.g., a human observer may not always be available to provide rewards, sensors may be limited or…

Machine Learning · Computer Science 2026-03-24 Alireza Kazemipour , Simone Parisi , Matthew E. Taylor , Michael Bowling

We study Concave Constrained Markov Decision Processes (Concave CMDPs) where both the objective and constraints are defined as concave functions of the state-action occupancy measure. We propose the Variance-Reduced Primal-Dual Policy…

Machine Learning · Computer Science 2024-05-28 Donghao Ying , Mengzi Amy Guo , Hyunin Lee , Yuhao Ding , Javad Lavaei , Zuo-Jun Max Shen

An optimal feedback controller for a given Markov decision process (MDP) can in principle be synthesized by value or policy iteration. However, if the system dynamics and the reward function are unknown, a learning agent must discover an…

Machine Learning · Computer Science 2019-07-19 Boris Belousov , Jan Peters

Multi-agent interactions are increasingly important in the context of reinforcement learning, and the theoretical foundations of policy gradient methods have attracted surging research interest. We investigate the global convergence of…

Optimization and Control · Mathematics 2023-03-21 Sarath Pattathil , Kaiqing Zhang , Asuman Ozdaglar

Policy gradient methods have become a standard for training reinforcement learning agents in a scalable and efficient manner. However, they do not account for transition uncertainty, whereas learning robust policies can be computationally…

Machine Learning · Computer Science 2023-12-12 Navdeep Kumar , Esther Derman , Matthieu Geist , Kfir Levy , Shie Mannor

While standard reinforcement learning optimizes a single reward signal, many applications require optimizing a nonlinear utility $f(J_1^\pi,\dots,J_M^\pi)$ over multiple objectives, where each $J_m^\pi$ denotes the expected discounted…

Machine Learning · Computer Science 2026-03-10 Swetha Ganesh , Vaneet Aggarwal

In many sequential decision-making problems one is interested in minimizing an expected cumulative cost while taking into account \emph{risk}, i.e., increased awareness of events of small probability and high consequences. Accordingly, the…

Artificial Intelligence · Computer Science 2017-04-07 Yinlam Chow , Mohammad Ghavamzadeh , Lucas Janson , Marco Pavone

We study the common generalization of Markov decision processes (MDPs) with sets of transition probabilities, known as robust MDPs (RMDPs). A standard goal in RMDPs is to compute a policy that maximizes the expected return under an…

Artificial Intelligence · Computer Science 2025-11-20 Alessandro Abate , Thom Badings , Giuseppe De Giacomo , Francesco Fabiano

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