Search Results for author: Peter Graf

Found 9 papers, 3 papers with code

Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks

no code implementations7 Feb 2024 Peter Graf, Patrick Emami

Models and policies that are simultaneously differentiable and interpretable may be key enablers of this marriage.

BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting

1 code implementation NeurIPS 2023 Patrick Emami, Abhijeet Sahu, Peter Graf

We also show that fine-tuning pretrained models on real commercial and residential buildings improves performance for a majority of target buildings.

Load Forecasting Transfer Learning

From Model-Based to Model-Free: Learning Building Control for Demand Response

1 code implementation18 Oct 2022 David Biagioni, Xiangyu Zhang, Christiane Adcock, Michael Sinner, Peter Graf, Jennifer King

We demonstrate, in this context, that hybrid methods offer many benefits over both purely model-free and model-based methods as long as certain requirements are met.

A Comparison of Model-Free and Model Predictive Control for Price Responsive Water Heaters

no code implementations8 Nov 2021 David J. Biagioni, Xiangyu Zhang, Peter Graf, Devon Sigler, Wesley Jones

We demonstrate that optimal control for this problem is challenging, requiring more than 8-hour lookahead for MPC with perfect forecasting to attain the minimum cost.

Model Predictive Control Time Series +1

Decentralized Cooperative Lane Changing at Freeway Weaving Areas Using Multi-Agent Deep Reinforcement Learning

no code implementations5 Oct 2021 Yi Hou, Peter Graf

The emergence of deep reinforcement learning (RL) and connected and automated vehicle technology provides a possible solution to improve mobility and energy efficiency at freeway bottlenecks through cooperative lane changing.

Reinforcement Learning (RL)

A Modular and Transferable Reinforcement Learning Framework for the Fleet Rebalancing Problem

no code implementations27 May 2021 Erotokritos Skordilis, Yi Hou, Charles Tripp, Matthew Moniot, Peter Graf, David Biagioni

To help bridge the gap between novel and existing methods, we propose a modular framework for fleet rebalancing based on model-free reinforcement learning (RL) that can leverage an existing dispatch method to minimize system cost.

Decision Making reinforcement-learning +2

K-spin Hamiltonian for quantum-resolvable Markov decision processes

no code implementations13 Apr 2020 Eric B. Jones, Peter Graf, Eliot Kapit, Wesley Jones

The Markov decision process is the mathematical formalization underlying the modern field of reinforcement learning when transition and reward functions are unknown.

Q-Learning Reinforcement Learning (RL)

Learning-Accelerated ADMM for Distributed Optimal Power Flow

no code implementations8 Nov 2019 David Biagioni, Peter Graf, Xiangyu Zhang, Ahmed Zamzam, Kyri Baker, Jennifer King

We propose a novel data-driven method to accelerate the convergence of Alternating Direction Method of Multipliers (ADMM) for solving distributed DC optimal power flow (DC-OPF) where lines are shared between independent network partitions.

Distributed Optimization

Matching Crystal Structures Atom-to-Atom

1 code implementation27 Sep 2019 Félix Therrien, Peter Graf, Vladan Stevanović

Finding an optimal match between two crystal structures underpins many important materials science problems including describing solid-solid phase transitions, developing models for interface and grain boundary structures, etc.

Materials Science Computational Physics

Cannot find the paper you are looking for? You can Submit a new open access paper.