A reinforcement learning framework for trajectory prediction under uncertainty and budget constraint

We consider the problem of trajectory prediction, where a trajectory is an ordered sequence of location visits and corresponding timestamps. The problem arises when an agent makes sequential decisions to visit a set of spatial locations of interest. Each location bears a stochastic utility and the a...

Full description

Saved in:
Bibliographic Details
Main Authors: LE, Truc Viet, LIU, Siyuan, LAU, Hoong Chuin
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2016
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/3364
https://ink.library.smu.edu.sg/context/sis_research/article/4366/viewcontent/ReinforcementLearningFramework.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-4366
record_format dspace
spelling sg-smu-ink.sis_research-43662018-03-09T09:09:38Z A reinforcement learning framework for trajectory prediction under uncertainty and budget constraint LE, Truc Viet LIU, Siyuan LAU, Hoong Chuin We consider the problem of trajectory prediction, where a trajectory is an ordered sequence of location visits and corresponding timestamps. The problem arises when an agent makes sequential decisions to visit a set of spatial locations of interest. Each location bears a stochastic utility and the agent has a limited budget to spend. Given the agent's observed partial trajectory, our goal is to predict the agent's remaining trajectory. We propose a solution framework to the problem that incorporates both the stochastic utility of each location and the budget constraint. We first cluster the agents into groups of homogeneous behaviors called "agent types". Depending on its type, each agent's trajectory is then transformed into a discrete-state sequence representation. Based on such representations, we use reinforcement learning (RL) to model the underlying decision processes and inverse RL to learn the utility distributions of the spatial locations. We finally propose two decision models to make predictions: one is based on long-term optimal planning of RL and another uses myopic heuristics. We apply the framework to predict real-world human trajectories collected in a large theme park and are able to explain the underlying processes of the observed actions. 2016-09-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/3364 info:doi/10.3233/978-1-61499-672-9-347 https://ink.library.smu.edu.sg/context/sis_research/article/4366/viewcontent/ReinforcementLearningFramework.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Artificial Intelligence and Robotics Computer Sciences Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Artificial Intelligence and Robotics
Computer Sciences
Numerical Analysis and Scientific Computing
spellingShingle Artificial Intelligence and Robotics
Computer Sciences
Numerical Analysis and Scientific Computing
LE, Truc Viet
LIU, Siyuan
LAU, Hoong Chuin
A reinforcement learning framework for trajectory prediction under uncertainty and budget constraint
description We consider the problem of trajectory prediction, where a trajectory is an ordered sequence of location visits and corresponding timestamps. The problem arises when an agent makes sequential decisions to visit a set of spatial locations of interest. Each location bears a stochastic utility and the agent has a limited budget to spend. Given the agent's observed partial trajectory, our goal is to predict the agent's remaining trajectory. We propose a solution framework to the problem that incorporates both the stochastic utility of each location and the budget constraint. We first cluster the agents into groups of homogeneous behaviors called "agent types". Depending on its type, each agent's trajectory is then transformed into a discrete-state sequence representation. Based on such representations, we use reinforcement learning (RL) to model the underlying decision processes and inverse RL to learn the utility distributions of the spatial locations. We finally propose two decision models to make predictions: one is based on long-term optimal planning of RL and another uses myopic heuristics. We apply the framework to predict real-world human trajectories collected in a large theme park and are able to explain the underlying processes of the observed actions.
format text
author LE, Truc Viet
LIU, Siyuan
LAU, Hoong Chuin
author_facet LE, Truc Viet
LIU, Siyuan
LAU, Hoong Chuin
author_sort LE, Truc Viet
title A reinforcement learning framework for trajectory prediction under uncertainty and budget constraint
title_short A reinforcement learning framework for trajectory prediction under uncertainty and budget constraint
title_full A reinforcement learning framework for trajectory prediction under uncertainty and budget constraint
title_fullStr A reinforcement learning framework for trajectory prediction under uncertainty and budget constraint
title_full_unstemmed A reinforcement learning framework for trajectory prediction under uncertainty and budget constraint
title_sort reinforcement learning framework for trajectory prediction under uncertainty and budget constraint
publisher Institutional Knowledge at Singapore Management University
publishDate 2016
url https://ink.library.smu.edu.sg/sis_research/3364
https://ink.library.smu.edu.sg/context/sis_research/article/4366/viewcontent/ReinforcementLearningFramework.pdf
_version_ 1770573124145774592