paper-with-me

Papers

A Sliding-Window Algorithm for Markov Decision Processes with Arbitrarily Changing Rewards and Transitions

2018-05-25 · Pratik Gajane, Ronald Ortner, Peter Auer

We consider reinforcement learning in changing Markov Decision Processes where both the state-transition probabilities and the reward functions may vary over time. For this problem setting, we propose an algorithm using a sliding window approach and provide performance guarantees for the regret evaluated against the optimal non-stationary policy. We also characterize the optimal window size suitable for our algorithm. These results are complemented by a sample complexity bound on the number of sub-optimal steps taken by the algorithm. Finally, we present some experimental results to support our theoretical analysis.

📄 PDF Abstract BibTeX arXiv:1805.10066

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Fast Automatic Feature Selection for Multi-Period Sliding Window Aggregate in Time Series

2020-12-02 · Rui An, Xingtian Shi, Baohan Xu

As one of the most well-known artificial feature sampler, the sliding window is widely used in scenarios where spatial and temporal information exists, such as computer vision, natural language process, data stream, and …

feature selectionTime SeriesTime Series Analysis

Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism

2020-06-24 · ICML 2020 1 · Wang Chi Cheung, David Simchi-Levi, Ruihao Zhu

We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under drifting non-stationarity, i.e., both the reward and state transition distributions are allowed to evolve over time, as long…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs

2021-10-18 · Han Zhong, Zhongren Chen, Zhuoran Yang, Zhaoran Wang 외

We study episodic reinforcement learning (RL) in non-stationary linear kernel Markov decision processes (MDPs). In this setting, both the reward function and the transition kernel are linear with respect to the given fea…

Reinforcement Learning (RL)

A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces

2020-07-09 · Omar Darwiche Domingues, Pierre Ménard, Matteo Pirotta, Emilie Kaufmann 외

In this work, we propose KeRNS: an algorithm for episodic reinforcement learning in non-stationary Markov Decision Processes (MDPs) whose state-action set is endowed with a metric. Using a non-parametric model of the MDP…

reinforcement-learningReinforcement Learning (RL)

Multiple Mean-Payoff Optimization under Local Stability Constraints

2024-12-17 · David Klaška, Antonín Kučera, Vojtěch Kůr, Vít Musil 외

The long-run average payoff per transition (mean payoff) is the main tool for specifying the performance and dependability properties of discrete systems. The problem of constructing a controller (strategy) simultaneousl…