Geoffrey Pettet
Research Subjects
Geoffrey Pettet has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Abhishek Dubey
Vanderbilt University, Nashville, USA
3 shared publications - Ayan Mukhopadhyay
Vanderbilt University, Nashville, USA
3 shared publications - Ayan Mukhopadhyay
Pontificia Universidad Católica de Valparaíso
1 shared publication - Baiting Luo
Vanderbilt University, Nashville, USA
1 shared publication - Christopher Kuhn
Technical University of Munich Germany
1 shared publication - Fangqi Liu
Vanderbilt University, Nashville, USA
1 shared publication
Latest Publications
- Open Access
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Online Decision-Making Under Uncertainty for Vehicle-to-Building Systems
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessOnline Decision-Making Under Uncertainty for Vehicle-to-Building Systems
- Open Access
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 177-186
Dynamic Simplex: Balancing Safety and Performance in Autonomous Cyber Physical Systems
- 9 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 177-186
Open AccessDynamic Simplex: Balancing Safety and Performance in Autonomous Cyber Physical Systems
- Open Access
- 31 October 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Cyber-Physical Systems
- Vol. 6 (4) , 1-26
Hierarchical Planning for Dynamic Resource Allocation in Smart and Connected Communities
Resource allocation under uncertainty is a classic problem in city-scale cyber-physical systems. Consider emergency response, where urban planners and first responders optimize the location of ambulances to minimize expected response times to incidents such as road accidents. Typically, such problems involve sequential decision making under uncertainty and can be modeled as Markov (or semi-Markov) decision processes. The goal of the decision maker is to learn a mapping from states to actions that can maximize expected rewards. While online, offline, and decentralized approaches have been proposed to tackle such problems, scalability remains a challenge for real world use cases. We present a general approach to hierarchical planning that leverages structure in city level CPS problems for resource allocation. We use emergency response as a case study and show how a large resource allocation problem can be split into smaller problems. We then use Monte Carlo planning for solving the smaller problems and managing the interaction between them. Finally, we use data from Nashville, Tennessee, a major metropolitan area in the United States, to validate our approach. Our experiments show that the proposed approach outperforms state-of-the-art approaches used in the field of emergency response.
- 31 October 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Cyber-Physical Systems
- Vol. 6 (4) , 1-26
Open AccessHierarchical Planning for Dynamic Resource Allocation in Smart and Connected Communities
Resource allocation under uncertainty is a classic problem in city-scale cyber-physical systems. Consider emergency response, where urban planners and first responders optimize the location of ambulances to minimize expected response times to incidents such as road accidents. Typically, such problems involve sequential decision making under uncertainty and can be modeled as Markov (or semi-Markov) decision processes. The goal of the decision maker is to learn a mapping from states to actions that can maximize expected rewards. While online, offline, and decentralized approaches have been proposed to tackle such problems, scalability remains a challenge for real world use cases. We present a general approach to hierarchical planning that leverages structure in city level CPS problems for resource allocation. We use emergency response as a case study and show how a large resource allocation problem can be split into smaller problems. We then use Monte Carlo planning for solving the smaller problems and managing the interaction between them. Finally, we use data from Nashville, Tennessee, a major metropolitan area in the United States, to validate our approach. Our experiments show that the proposed approach outperforms state-of-the-art approaches used in the field of emergency response.
- Open Access
Decision Making in Non-Stationary Environments with Policy-Augmented Monte Carlo Tree Search
Decision-making under uncertainty (DMU) is present in many important problems. An open challenge is DMU in non-stationary environments, where the dynamics of the environment can change over time. Reinforcement Learning (RL), a popular approach for DMU problems, learns a policy by interacting with a model of the environment offline. Unfortunately, if the environment changes the policy can become stale and take sub-optimal actions, and relearning the policy for the updated environment takes time and computational effort. An alternative is online planning approaches such as Monte Carlo Tree Search (MCTS), which perform their computation at decision time. Given the current environment, MCTS plans using high-fidelity models to determine promising action trajectories. These models can be updated as soon as environmental changes are detected to immediately incorporate them into decision making. However, MCTS's convergence can be slow for domains with large state-action spaces. In this paper, we present a novel hybrid decision-making approach that combines the strengths of RL and planning while mitigating their weaknesses. Our approach, called Policy Augmented MCTS (PA-MCTS), integrates a policy's actin-value estimates into MCTS, using the estimates to seed the action trajectories favored by the search. We hypothesize that PA-MCTS will converge more quickly than standard MCTS while making better decisions than the policy can make on its own when faced with nonstationary environments. We test our hypothesis by comparing PA-MCTS with pure MCTS and an RL agent applied to the classical CartPole environment. We find that PC-MCTS can achieve higher cumulative rewards than the policy in isolation under several environmental shifts while converging in significantly fewer iterations than pure MCTS.
Open AccessDecision Making in Non-Stationary Environments with Policy-Augmented Monte Carlo Tree Search
Decision-making under uncertainty (DMU) is present in many important problems. An open challenge is DMU in non-stationary environments, where the dynamics of the environment can change over time. Reinforcement Learning (RL), a popular approach for DMU problems, learns a policy by interacting with a model of the environment offline. Unfortunately, if the environment changes the policy can become stale and take sub-optimal actions, and relearning the policy for the updated environment takes time and computational effort. An alternative is online planning approaches such as Monte Carlo Tree Search (MCTS), which perform their computation at decision time. Given the current environment, MCTS plans using high-fidelity models to determine promising action trajectories. These models can be updated as soon as environmental changes are detected to immediately incorporate them into decision making. However, MCTS's convergence can be slow for domains with large state-action spaces. In this paper, we present a novel hybrid decision-making approach that combines the strengths of RL and planning while mitigating their weaknesses. Our approach, called Policy Augmented MCTS (PA-MCTS), integrates a policy's actin-value estimates into MCTS, using the estimates to seed the action trajectories favored by the search. We hypothesize that PA-MCTS will converge more quickly than standard MCTS while making better decisions than the policy can make on its own when faced with nonstationary environments. We test our hypothesis by comparing PA-MCTS with pure MCTS and an RL agent applied to the classical CartPole environment. We find that PC-MCTS can achieve higher cumulative rewards than the policy in isolation under several environmental shifts while converging in significantly fewer iterations than pure MCTS.