English
Related papers

Related papers: Regret Analysis of Policy Gradient Algorithm for I…

200 papers

In this paper, we investigate the concentration properties of cumulative reward in Markov Decision Processes (MDPs), focusing on both asymptotic and non-asymptotic settings. We introduce a unified approach to characterize reward…

Machine Learning · Computer Science 2025-12-04 Borna Sayedana , Peter E. Caines , Aditya Mahajan

Recently, model-free reinforcement learning has attracted research attention due to its simplicity, memory and computation efficiency, and the flexibility to combine with function approximation. In this paper, we propose Exploration…

Machine Learning · Computer Science 2020-12-10 Mehdi Jafarnia-Jahromi , Chen-Yu Wei , Rahul Jain , Haipeng Luo

We study reinforcement learning for continuous-time Markov decision processes (MDPs) in the finite-horizon episodic setting. In contrast to discrete-time MDPs, the inter-transition times of a continuous-time MDP are exponentially…

Machine Learning · Computer Science 2023-10-04 Xuefeng Gao , Xun Yu Zhou

We study infinite-horizon average-reward Markov decision processes (AMDPs) in the context of general function approximation. Specifically, we propose a novel algorithmic framework named Local-fitted Optimization with OPtimism (LOOP), which…

Machine Learning · Computer Science 2024-04-22 Jianliang He , Han Zhong , Zhuoran Yang

Policy design in non-stationary Markov Decision Processes (MDPs) is inherently challenging due to the complexities introduced by time-varying system transition and reward, which make it difficult for learners to determine the optimal…

Machine Learning · Computer Science 2025-11-17 Ziyi Zhang , Yorie Nakahira , Guannan Qu

We study online finite-horizon Markov Decision Processes with adversarially changing loss and aggregate bandit feedback (a.k.a full-bandit). Under this type of feedback, the agent observes only the total loss incurred over the entire…

Machine Learning · Computer Science 2025-02-07 Tal Lancewicki , Yishay Mansour

We consider Markov Decision Processes (MDPs) with deterministic transitions and study the problem of regret minimization, which is central to the analysis and design of optimal learning algorithms. We present logarithmic problem-specific…

Machine Learning · Computer Science 2021-06-29 Damianos Tranos , Alexandre Proutiere

We present an algorithm based on posterior sampling (aka Thompson sampling) that achieves near-optimal worst-case regret bounds when the underlying Markov Decision Process (MDP) is communicating with a finite, though unknown, diameter. Our…

Machine Learning · Computer Science 2020-04-01 Shipra Agrawal , Randy Jia

In this paper, we present algorithms that perform gradient ascent of the average reward in a partially observable Markov decision process (POMDP). These algorithms are based on GPOMDP, an algorithm introduced in a companion paper (Baxter…

Artificial Intelligence · Computer Science 2019-11-18 J. Baxter , P. L. Bartlett , L. Weaver

This paper develops a viable notion of learning for sampling-based algorithms that applies in broader settings than previously considered. More specifically, we model a discounted infinite-horizon MDPs with Borel state and action spaces,…

Machine Learning · Statistics 2026-04-09 Daniel Adelman , Cagla Keceli , Alba V. Olivares-Nadal

We introduce \texttt{OPO-CMDP}, the first policy optimization algorithm for stochastic Contextual Markov Decision Process (CMDPs) under general offline function approximation. Our approach achieves a high probability regret bound of…

Machine Learning · Computer Science 2026-02-17 Orin Levy , Aviv Rosenberg , Alon Cohen , Yishay Mansour

We tackle average-reward infinite-horizon POMDPs with an unknown transition model but a known observation model, a setting that has been previously addressed in two limiting ways: (i) frequentist methods relying on suboptimal stochastic…

Machine Learning · Computer Science 2025-09-09 Alessio Russo , Alberto Maria Metelli , Marcello Restelli

Constrained Markov Decision Processes (CMDPs) are one of the common ways to model safe reinforcement learning problems, where constraint functions model the safety objectives. Lagrangian-based dual or primal-dual algorithms provide…

Machine Learning · Computer Science 2023-08-31 Adrian Müller , Pragnya Alatur , Giorgia Ramponi , Niao He

We study Markov Decision Processes (MDP) wherein states correspond to causal graphs that stochastically generate rewards. In this setup, the learner's goal is to identify atomic interventions that lead to high rewards by intervening on…

Machine Learning · Computer Science 2021-11-02 Rahul Madhavan , Aurghya Maiti , Gaurav Sinha , Siddharth Barman

We consider undiscounted reinforcement learning in Markov decision processes (MDPs) where both the reward functions and the state-transition probabilities may vary (gradually or abruptly) over time. For this problem setting, we propose an…

Machine Learning · Computer Science 2019-09-11 Pratik Gajane , Ronald Ortner , Peter Auer

We study regret minimization for reinforcement learning (RL) in Latent Markov Decision Processes (LMDPs) with context in hindsight. We design a novel model-based algorithmic framework which can be instantiated with both a model-optimistic…

Machine Learning · Computer Science 2023-05-23 Runlong Zhou , Ruosong Wang , Simon S. Du

We consider learning in an adversarial Markov Decision Process (MDP) where the loss functions can change arbitrarily over $K$ episodes and the state space can be arbitrarily large. We assume that the Q-function of any policy is linear in…

Machine Learning · Computer Science 2023-06-05 Yan Dai , Haipeng Luo , Chen-Yu Wei , Julian Zimmert

A standard assumption in Reinforcement Learning is that the agent observes every visited state-action pair in the associated Markov Decision Process (MDP), along with the per-step rewards. Strong theoretical results are known in this…

Machine Learning · Computer Science 2026-02-03 Zhengjia Zhuo , Anupam Gupta , Viswanath Nagarajan

This work studies online episodic tabular Markov decision processes (MDPs) with known transitions and develops best-of-both-worlds algorithms that achieve refined data-dependent regret bounds in the adversarial regime and variance-dependent…

Machine Learning · Computer Science 2026-02-03 Mingyi Li , Taira Tsuchiya , Kenji Yamanishi

Solving Partially Observable Markov Decision Processes (POMDPs) is hard. Learning optimal controllers for POMDPs when the model is unknown is harder. Online learning of optimal controllers for unknown POMDPs, which requires efficient…

Machine Learning · Computer Science 2021-06-16 Mehdi Jafarnia-Jahromi , Rahul Jain , Ashutosh Nayyar