English
Related papers

Related papers: Geometry of Drifting MDPs with Path-Integral Stabi…

200 papers

Model-based offline reinforcement learning (RL) aims to find highly rewarding policy, by leveraging a previously collected static dataset and a dynamics model. While the dynamics model learned through reuse of the static dataset, its…

Machine Learning · Computer Science 2022-11-01 Kaiyang Guo , Yunfeng Shao , Yanhui Geng

We study model-based reinforcement learning (RL) for episodic Markov decision processes (MDP) whose transition probability is parametrized by an unknown transition core with features of state and action. Despite much recent progress in…

Machine Learning · Statistics 2024-11-19 Taehyun Hwang , Min-hwan Oh

The standard RL world model is that of a Markov Decision Process (MDP). A basic premise of MDPs is that the rewards depend on the last state and action only. Yet, many real-world rewards are non-Markovian. For example, a reward for bringing…

Artificial Intelligence · Computer Science 2019-12-06 Maor Gaon , Ronen I. Brafman

Robust Markov decision processes (MDPs) address the challenge of model uncertainty by optimizing the worst-case performance over an uncertainty set of MDPs. In this paper, we focus on the robust average-reward MDPs under the model-free…

Machine Learning · Computer Science 2023-05-19 Yue Wang , Alvaro Velasquez , George Atia , Ashley Prater-Bennette , Shaofeng Zou

In real scenarios, state observations that an agent observes may contain measurement errors or adversarial noises, misleading the agent to take suboptimal actions or even collapse while training. In this paper, we study the training…

Machine Learning · Computer Science 2023-06-23 Ke Sun , Yingnan Zhao , Shangling Jui , Linglong Kong

Reinforcement learning (RL) methods often rely on massive exploration data to search optimal policies, and suffer from poor sampling efficiency. This paper presents a mixed reinforcement learning (mixed RL) algorithm by simultaneously using…

Systems and Control · Electrical Eng. & Systems 2020-03-03 Yao Mu , Shengbo Eben Li , Chang Liu , Qi Sun , Bingbing Nie , Bo Cheng , Baiyu Peng

The suspension system is a crucial part of the automotive chassis, improving vehicle ride comfort and isolating passengers from rough road excitation. Unlike passive suspension, which has constant spring and damping coefficients, active…

Robotics · Computer Science 2024-08-19 Anh N. Nhu , Ngoc-Anh Le , Shihang Li , Thang D. V. Truong

Training reinforcement learning (RL) agents using scalar reward signals is often infeasible when an environment has sparse and non-Markovian rewards. Moreover, handcrafting these reward functions before training is prone to…

Machine Learning · Computer Science 2023-10-04 Alessandro Abate , Yousif Almulla , James Fox , David Hyland , Michael Wooldridge

Reinforcement learning is an emerging approaches to facilitate multi-stage sequential decision-making problems. This paper studies a real-time multi-stage stochastic power dispatch considering multivariate uncertainties. Current researches…

Machine Learning · Computer Science 2024-01-24 Bairong Deng , Tao Yu , Zhenning Pan , Xuehan Zhang , Yufeng Wu , Qiaoyi Ding

Understanding customer movement within retail spaces is essential for optimizing store layouts. Real-world trajectory data can provide highly accurate insights, but collecting it is costly and often infeasible for many retailers. Heuristics…

Machine Learning · Computer Science 2026-05-19 Ken Ming Lee , Paul Barde , Maxime C. Cohen , Derek Nowrouzezahrai

We study multi-objective reinforcement learning with nonlinear preferences over trajectories. That is, we maximize the expected value of a nonlinear function over accumulated rewards (expected scalarized return or ESR) in a multi-objective…

Machine Learning · Computer Science 2025-02-19 Nianli Peng , Muhang Tian , Brandon Fain

Simultaneous Localization and Planning (SLAP) under process and measurement uncertainties is a challenge. It involves solving a stochastic control problem modeled as a Partially Observed Markov Decision Process (POMDP) in a general…

Robotics · Computer Science 2016-08-12 Mohammadhussein Rafieisakhaei , Suman Chakravorty , P. R. Kumar

This paper considers random access in deadline-constrained broadcasting with frame-synchronized traffic. To enhance the maximum achievable timely delivery ratio (TDR), we define a dynamic control scheme that allows each active node to…

Systems and Control · Electrical Eng. & Systems 2021-08-09 Aoyu Gong , Lei Deng , Fang Liu , Yijin Zhang

We study off-dynamics Reinforcement Learning (RL), where the policy is trained on a source domain and deployed to a distinct target domain. We aim to solve this problem via online distributionally robust Markov decision processes (DRMDPs),…

Machine Learning · Computer Science 2024-02-26 Zhishuai Liu , Pan Xu

Ensuring safety in autonomous vehicles necessitates advanced path planning and obstacle avoidance capabilities, particularly in dynamic environments. This paper introduces a bi-level control framework that efficiently augments road…

Robotics · Computer Science 2025-10-07 Mostafa Emam , Matthias Gerdts

Passive reaction effects in grasp stability analysis occur when the contact forces and joint torques applied by a grasp change in response to external disturbances applied to the grasped object. For example, nonbackdrivable actuators (e.g.…

Robotics · Computer Science 2020-07-10 Maximilian Haas-Heger , Matei Ciocarlie

We study learning in periodic Markov Decision Process(MDP), a special type of non-stationary MDP where both the state transition probabilities and reward functions vary periodically, under the average reward maximization setting. We…

Machine Learning · Computer Science 2022-07-26 Ayush Aniket , Arpan Chattopadhyay

In many real-world scenarios, Reinforcement Learning (RL) algorithms are trained on data with dynamics shift, i.e., with different underlying environment dynamics. A majority of current methods address such issue by training context…

Machine Learning · Computer Science 2024-02-23 Zhenghai Xue , Qingpeng Cai , Shuchang Liu , Dong Zheng , Peng Jiang , Kun Gai , Bo An

We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on…

Deploying reinforcement learning policies in the real world requires adapting to time-varying environments. We study this problem in the contextual Markov Decision Process (cMDP) framework, where a family of environments is indexed by a…

Machine Learning · Computer Science 2026-05-04 Param Budhraja , Aditya Gangrade , Alex Olshevsky , Venkatesh Saligrama