Reinforcement learning framework for modeling spatial sequential decisions under uncertainty: (Extended abstract)
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...
Saved in:
Main Authors: | , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2016
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/3403 https://ink.library.smu.edu.sg/context/sis_research/article/4404/viewcontent/ReinforcementLearningRameworkSSD_AAMAS_2016.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-4404 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-44042018-03-08T06:30:53Z Reinforcement learning framework for modeling spatial sequential decisions under uncertainty: (Extended abstract) 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 remaining trajectory. We propose a solution framework to the problem considering both the uncertainty of utility and the budget constraint. We use reinforcement learning (RL) to model the underlying decision processes and inverse RL to learn the utility distributions of the locations. We then propose two decision models to make predictions: one is based on long-term optimal planning of RL and another uses myopic heuristics. We finally apply the framework to predict real-world human trajectories and are able to explain the underlying processes of the observed actions. 2016-05-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/3403 https://ink.library.smu.edu.sg/context/sis_research/article/4404/viewcontent/ReinforcementLearningRameworkSSD_AAMAS_2016.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 reinforcement learning budget constraint stochastic utility markov decision process sequential decisions trajectory prediction Artificial Intelligence and Robotics Computer Sciences Operations Research, Systems Engineering and Industrial Engineering |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
reinforcement learning budget constraint stochastic utility markov decision process sequential decisions trajectory prediction Artificial Intelligence and Robotics Computer Sciences Operations Research, Systems Engineering and Industrial Engineering |
spellingShingle |
reinforcement learning budget constraint stochastic utility markov decision process sequential decisions trajectory prediction Artificial Intelligence and Robotics Computer Sciences Operations Research, Systems Engineering and Industrial Engineering LE, Truc Viet LIU, Siyuan LAU, Hoong Chuin Reinforcement learning framework for modeling spatial sequential decisions under uncertainty: (Extended abstract) |
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 remaining trajectory. We propose a solution framework to the problem considering both the uncertainty of utility and the budget constraint. We use reinforcement learning (RL) to model the underlying decision processes and inverse RL to learn the utility distributions of the locations. We then propose two decision models to make predictions: one is based on long-term optimal planning of RL and another uses myopic heuristics. We finally apply the framework to predict real-world human trajectories 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 |
Reinforcement learning framework for modeling spatial sequential decisions under uncertainty: (Extended abstract) |
title_short |
Reinforcement learning framework for modeling spatial sequential decisions under uncertainty: (Extended abstract) |
title_full |
Reinforcement learning framework for modeling spatial sequential decisions under uncertainty: (Extended abstract) |
title_fullStr |
Reinforcement learning framework for modeling spatial sequential decisions under uncertainty: (Extended abstract) |
title_full_unstemmed |
Reinforcement learning framework for modeling spatial sequential decisions under uncertainty: (Extended abstract) |
title_sort |
reinforcement learning framework for modeling spatial sequential decisions under uncertainty: (extended abstract) |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2016 |
url |
https://ink.library.smu.edu.sg/sis_research/3403 https://ink.library.smu.edu.sg/context/sis_research/article/4404/viewcontent/ReinforcementLearningRameworkSSD_AAMAS_2016.pdf |
_version_ |
1770573160980152320 |