English
Related papers

Related papers: Online Planning with Lookahead Policies

200 papers

We study reward-free reinforcement learning (RL) with linear function approximation, where the agent works in two phases: (1) in the exploration phase, the agent interacts with the environment but cannot access the reward; and (2) in the…

Machine Learning · Computer Science 2024-02-15 Junkai Zhang , Weitong Zhang , Quanquan Gu

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

Online planning for partially observable Markov decision processes (POMDPs) provides efficient techniques for robot decision-making under uncertainty. However, existing methods fall short of preventing safety violations in dynamic…

Robotics · Computer Science 2024-09-10 Shili Sheng , Pian Yu , David Parker , Marta Kwiatkowska , Lu Feng

Ready Mixed Concrete Delivery Problem (RMCDP) is a multi-objective multi-constraint dynamic combinatorial optimization problem. From the operational research prospective, it is a real life logistic problem that is hard to be solved with…

Data Structures and Algorithms · Computer Science 2018-10-29 Mohamed Masoud , Saeid Belkasim

In this paper we consider infinite horizon discounted dynamic programming problems with finite state and control spaces, partial state observations, and a multiagent structure. We discuss and compare algorithms that simultaneously or…

Robotics · Computer Science 2020-11-10 Sushmita Bhattacharya , Siva Kailas , Sahil Badyal , Stephanie Gil , Dimitri Bertsekas

This paper presents a novel method of global adaptive dynamic programming (ADP) for the adaptive optimal control of nonlinear polynomial systems. The strategy consists of relaxing the problem of solving the Hamilton-Jacobi-Bellman (HJB)…

Dynamical Systems · Mathematics 2017-01-11 Yu Jiang , Zhong-Ping Jiang

This paper studies the online optimal control problem with time-varying convex stage costs for a time-invariant linear dynamical system, where a finite lookahead window of accurate predictions of the stage costs are available at each time.…

Optimization and Control · Mathematics 2019-10-23 Yingying Li , Xin Chen , Na Li

Differential Dynamic Programming (DDP) is an efficient computational tool for solving nonlinear optimal control problems. It was originally designed as a single shooting method and thus is sensitive to the initial guess supplied. This work…

Robotics · Computer Science 2023-09-29 He Li , Wenhao Yu , Tingnan Zhang , Patrick M. Wensing

In this paper we propose an on-line policy iteration (PI) algorithm for finite-state infinite horizon discounted dynamic programming, whereby the policy improvement operation is done on-line, only for the states that are encountered during…

Optimization and Control · Mathematics 2021-06-03 Dimitri Bertsekas

Deep Reinforcement Learning (DRL) has made considerable advances in simulated and physical robot control tasks, especially when problems admit a fully observed Markov Decision Process (MDP) formulation. When observations only partially…

Robotics · Computer Science 2026-03-24 Lingheng Meng , Rob Gorbet , Michael Burke , Dana Kulić

Sequential decision problems in applications such as manipulation in warehouses, multi-step meal preparation, and routing in autonomous vehicle networks often involve reasoning about uncertainty, planning over discrete modes as well as…

Artificial Intelligence · Computer Science 2019-06-24 Shushman Choudhury , Mykel J. Kochenderfer

The partially observable Markov decision process (POMDP) provides a principled general framework for planning under uncertainty, but solving POMDPs optimally is computationally intractable, due to the "curse of dimensionality" and the…

Artificial Intelligence · Computer Science 2017-09-20 Nan Ye , Adhiraj Somani , David Hsu , Wee Sun Lee

We study offline reinforcement learning under a novel model called strategic MDP, which characterizes the strategic interactions between a principal and a sequence of myopic agents with private types. Due to the bilevel structure and…

Machine Learning · Statistics 2022-08-24 Mengxin Yu , Zhuoran Yang , Jianqing Fan

This paper presents a two-step algorithm for online trajectory planning in indoor environments with unknown obstacles. In the first step, sampling-based path planning techniques such as the optimal Rapidly exploring Random Tree (RRT*)…

Robotics · Computer Science 2023-02-07 Martin Zimmermann , Minh Nhat Vu , Florian Beck , Anh Nguyen , Andreas Kugi

We present a general framework for applying learning algorithms and heuristical guidance to the verification of Markov decision processes (MDPs). The primary goal of our techniques is to improve performance by avoiding an exhaustive…

To operate with limited sensor horizons in unpredictable environments, autonomous robots use a receding-horizon strategy to plan trajectories, wherein they execute a short plan while creating the next plan. However, creating safe,…

Robotics · Computer Science 2020-04-24 Shreyas Kousik , Sean Vaskov , Fan Bu , Matthew Johnson-Roberson , Ram Vasudevan

This paper introduces a novel Differential Dynamic Programming (DDP) algorithm for solving discrete-time finite-horizon optimal control problems with inequality constraints. Two variants, namely Feasible- and Infeasible-IPDDP algorithms,…

Systems and Control · Electrical Eng. & Systems 2020-10-21 Andrei Pavlov , Iman Shames , Chris Manzie

Optimal control (OC) algorithms such as Differential Dynamic Programming (DDP) take advantage of the derivatives of the dynamics to efficiently control physical systems. Yet, in the presence of nonsmooth dynamical systems, such class of…

Online planning under uncertainty in partially observable domains is an essential capability in robotics and AI. The partially observable Markov decision process (POMDP) is a mathematically principled framework for addressing…

Robotics · Computer Science 2024-10-14 Da Kong , Vadim Indelman

We consider online reinforcement learning (RL) in episodic Markov decision processes (MDPs) under the linear $q^\pi$-realizability assumption, where it is assumed that the action-values of all policies can be expressed as linear functions…

Machine Learning · Computer Science 2023-12-21 Gellért Weisz , András György , Csaba Szepesvári
‹ Prev 1 4 5 6 7 8 10 Next ›