English
Related papers

Related papers: Offline Oracle-Efficient Learning for Contextual M…

200 papers

We present the E-UC$^3$RL algorithm for regret minimization in Stochastic Contextual Markov Decision Processes (CMDPs). The algorithm operates under the minimal assumptions of realizable function class and access to \emph{offline} least…

Machine Learning · Computer Science 2024-05-30 Orin Levy , Asaf Cassel , Alon Cohen , Yishay Mansour

In the reinforcement learning literature, there are many algorithms developed for either Contextual Bandit (CB) or Markov Decision Processes (MDP) environments. However, when deploying reinforcement learning algorithms in the real world,…

Machine Learning · Computer Science 2022-08-02 Kelly W. Zhang , Omer Gottesman , Finale Doshi-Velez

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

This work studies the statistical limits of uniform convergence for offline policy evaluation (OPE) problems with model-based methods (for episodic MDP) and provides a unified framework towards optimal learning for several well-motivated…

Machine Learning · Computer Science 2021-06-25 Ming Yin , Yu-Xiang Wang

Offline estimation of the dynamical model of a Markov Decision Process (MDP) is a non-trivial task that greatly depends on the data available in the learning phase. Sometimes the dynamics of the model is invariant with respect to some…

Machine Learning · Computer Science 2023-04-13 Giorgio Angelotti , Nicolas Drougard , Caroline P. C. Chanel

We consider the problem of offline reinforcement learning (RL) -- a well-motivated setting of RL that aims at policy optimization using only historical data. Despite its wide applicability, theoretical understandings of offline RL, such as…

Machine Learning · Computer Science 2021-02-04 Ming Yin , Yu Bai , Yu-Xiang Wang

Contextual Markov decision processes (CMDPs) describe a class of reinforcement learning problems in which the transition kernels and reward functions can change over time with different MDPs indexed by a context variable. While CMDPs serve…

Machine Learning · Computer Science 2024-02-06 Junze Deng , Yuan Cheng , Shaofeng Zou , Yingbin Liang

We consider offline reinforcement learning (RL) in $H$-horizon Markov decision processes (MDPs) under the linear $q^\pi$-realizability assumption, where the action-value function of every policy is linear with respect to a given…

Machine Learning · Computer Science 2024-05-28 Volodymyr Tkachuk , Gellért Weisz , Csaba Szepesvári

We study reinforcement learning with function approximation for large-scale Partially Observable Markov Decision Processes (POMDPs) where the state space and observation space are large or even continuous. Particularly, we consider Hilbert…

Machine Learning · Computer Science 2022-06-27 Masatoshi Uehara , Ayush Sekhari , Jason D. Lee , Nathan Kallus , Wen Sun

We consider online learning for episodic stochastically constrained Markov decision processes (CMDPs), which plays a central role in ensuring the safety of reinforcement learning. Here the loss function can vary arbitrarily across the…

Machine Learning · Computer Science 2021-10-19 Shuang Qiu , Xiaohan Wei , Zhuoran Yang , Jieping Ye , Zhaoran Wang

We study the Safe Reinforcement Learning (SRL) problem using the Constrained Markov Decision Process (CMDP) formulation in which an agent aims to maximize the expected total reward subject to a safety constraint on the expected total value…

Machine Learning · Computer Science 2020-10-27 Dongsheng Ding , Xiaohan Wei , Zhuoran Yang , Zhaoran Wang , Mihailo R. Jovanović

The problem of offline reinforcement learning focuses on learning a good policy from a log of environment interactions. Past efforts for developing algorithms in this area have revolved around introducing constraints to online reinforcement…

Machine Learning · Computer Science 2022-04-27 Ian Char , Viraj Mehta , Adam Villaflor , John M. Dolan , Jeff Schneider

We consider the recently proposed reinforcement learning (RL) framework of Contextual Markov Decision Processes (CMDP), where the agent interacts with a (potentially adversarial) sequence of episodic tabular MDPs. In addition, a context…

Machine Learning · Computer Science 2020-06-19 Aditya Modi , Ambuj Tewari

Exploration is a major challenge in reinforcement learning, especially for high-dimensional domains that require function approximation. We propose exploration objectives -- policy optimization objectives that enable downstream maximization…

Machine Learning · Computer Science 2024-06-06 Philip Amortila , Dylan J. Foster , Akshay Krishnamurthy

We consider online reinforcement learning in episodic Markov decision process (MDP) with unknown transition function and stochastic rewards drawn from some fixed but unknown distribution. The learner aims to learn the optimal policy and…

Machine Learning · Computer Science 2024-03-12 Vincent Leon , S. Rasoul Etesami

This paper addresses the poor finite-horizon performance of existing online \emph{restless bandit} (RB) algorithms, which stems from the prohibitive sample complexity of learning a full \emph{Markov decision process} (MDP) for each agent.…

Machine Learning · Computer Science 2026-04-07 Jiamin Xu , Ivan Nazarov , Aditya Rastogi , África Periáñez , Kyra Gan

This work studies offline Reinforcement Learning (RL) in a class of non-Markovian environments called Regular Decision Processes (RDPs). In RDPs, the unknown dependency of future observations and rewards from the past interactions can be…

Machine Learning · Computer Science 2024-09-05 Ahana Deb , Roberto Cipollone , Anders Jonsson , Alessandro Ronca , Mohammad Sadegh Talebi

In Markov decision processes (MDPs), quantile risk measures such as Value-at-Risk are a standard metric for modeling RL agents' preferences for certain outcomes. This paper proposes a new Q-learning algorithm for quantile optimization in…

Machine Learning · Computer Science 2024-11-01 Jia Lin Hau , Erick Delage , Esther Derman , Mohammad Ghavamzadeh , Marek Petrik

Reinforcement learning with outcome-based feedback faces a fundamental challenge: when rewards are only observed at trajectory endpoints, how do we assign credit to the right actions? This paper provides the first comprehensive analysis of…

Machine Learning · Computer Science 2025-07-25 Fan Chen , Zeyu Jia , Alexander Rakhlin , Tengyang Xie

We study learning optimal policies from a logged dataset, i.e., offline RL, with function approximation. Despite the efforts devoted, existing algorithms with theoretic finite-sample guarantees typically assume exploratory data coverage or…

Machine Learning · Computer Science 2023-05-25 Chenjie Mao