paper-with-me

홈 › Papers

Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning

2019-12-01 · NeurIPS 2019 12 · Erwan Lecarpentier, Emmanuel Rachelson

This work tackles the problem of robust zero-shot planning in non-stationary stochastic environments. We study Markov Decision Processes (MDPs) evolving over time and consider Model-Based Reinforcement Learning algorithms in this setting. We make two hypotheses: 1) the environment evolves continuously with a bounded evolution rate; 2) a current model is known at each decision epoch but not its evolution. Our contribution can be presented in four points. 1) we define a specific class of MDPs that we call Non-Stationary MDPs (NSMDPs). We introduce the notion of regular evolution by making an hypothesis of Lipschitz-Continuity on the transition and reward functions w.r.t. time; 2) we consider a planning agent using the current model of the environment but unaware of its future evolution. This leads us to consider a worst-case method where the environment is seen as an adversarial agent; 3) following this approach, we propose the Risk-Averse Tree-Search (RATS) algorithm, a zero-shot Model-Based method similar to Minimax search; 4) we illustrate the benefits brought by RATS empirically and compare its performance with reference Model-Based algorithms.

📄 PDF Abstract BibTeX

Code (1)

SuReLI/rats-experiments 공식 구현

Tasks

Model-based Reinforcement LearningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version

2019-04-22 · Erwan Lecarpentier, Emmanuel Rachelson

This work tackles the problem of robust zero-shot planning in non-stationary stochastic environments. We study Markov Decision Processes (MDPs) evolving over time and consider Model-Based Reinforcement Learning algorithm…

Model-based Reinforcement LearningReinforcement Learning

Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints

2024-05-23 · Francesco Emanuele Stradi, Anna Lunghi, Matteo Castiglioni, Alberto Marchesi 외

In constrained Markov decision processes (CMDPs) with adversarial rewards and constraints, a well-known impossibility result prevents any algorithm from attaining both sublinear regret and sublinear constraint violation,…

Square-root regret bounds for continuous-time episodic Markov decision processes

2022-10-03 · Xuefeng Gao, Xun Yu Zhou

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 expo…

reinforcement-learningReinforcement Learning (RL)

Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration

2020-10-23 · Priyank Agrawal, Jinglin Chen, Nan Jiang

This paper studies regret minimization with randomized value functions in reinforcement learning. In tabular finite-horizon Markov Decision Processes, we introduce a clipping variant of one classical Thompson Sampling (T…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Thompson Sampling

Planning in entropy-regularized Markov decision processes and games

2026-04-21 · Jean-Bastien Grill, Omar Darwiche Domingues, Pierre Ménard, Rémi Munos 외 arxiv

We propose SmoothCruiser, a new planning algorithm for estimating the value function in entropy-regularized Markov decision processes and two-player games, given a generative model of the environment. SmoothCruiser makes…