Picture for Lucas Spangher

Lucas Spangher

Project MPG: towards a generalized performance benchmark for LLM capabilities

Add code
Oct 28, 2024
Viaarxiv icon

Time Series Viewmakers for Robust Disruption Prediction

Add code
Oct 14, 2024
Viaarxiv icon

Offline Regularised Reinforcement Learning for Large Language Models Alignment

Add code
May 29, 2024
Viaarxiv icon

Active Reinforcement Learning for Robust Building Control

Add code
Dec 16, 2023
Viaarxiv icon

Continuous Convolutional Neural Networks for Disruption Prediction in Nuclear Fusion Plasmas

Add code
Dec 03, 2023
Viaarxiv icon

Machine Learning for Smart and Energy-Efficient Buildings

Add code
Nov 27, 2022
Viaarxiv icon

Personalized Federated Hypernetworks for Privacy Preservation in Multi-Task Reinforcement Learning

Add code
Oct 19, 2022
Figure 1 for Personalized Federated Hypernetworks for Privacy Preservation in Multi-Task Reinforcement Learning
Figure 2 for Personalized Federated Hypernetworks for Privacy Preservation in Multi-Task Reinforcement Learning
Figure 3 for Personalized Federated Hypernetworks for Privacy Preservation in Multi-Task Reinforcement Learning
Figure 4 for Personalized Federated Hypernetworks for Privacy Preservation in Multi-Task Reinforcement Learning
Viaarxiv icon

Adapting Surprise Minimizing Reinforcement Learning Techniques for Transactive Control

Add code
Nov 11, 2021
Figure 1 for Adapting Surprise Minimizing Reinforcement Learning Techniques for Transactive Control
Figure 2 for Adapting Surprise Minimizing Reinforcement Learning Techniques for Transactive Control
Figure 3 for Adapting Surprise Minimizing Reinforcement Learning Techniques for Transactive Control
Viaarxiv icon

Offline-Online Reinforcement Learning for Energy Pricing in Office Demand Response: Lowering Energy and Data Costs

Add code
Aug 14, 2021
Figure 1 for Offline-Online Reinforcement Learning for Energy Pricing in Office Demand Response: Lowering Energy and Data Costs
Figure 2 for Offline-Online Reinforcement Learning for Energy Pricing in Office Demand Response: Lowering Energy and Data Costs
Figure 3 for Offline-Online Reinforcement Learning for Energy Pricing in Office Demand Response: Lowering Energy and Data Costs
Figure 4 for Offline-Online Reinforcement Learning for Energy Pricing in Office Demand Response: Lowering Energy and Data Costs
Viaarxiv icon

Using Meta Reinforcement Learning to Bridge the Gap between Simulation and Experiment in Energy Demand Response

Add code
May 17, 2021
Figure 1 for Using Meta Reinforcement Learning to Bridge the Gap between Simulation and Experiment in Energy Demand Response
Figure 2 for Using Meta Reinforcement Learning to Bridge the Gap between Simulation and Experiment in Energy Demand Response
Figure 3 for Using Meta Reinforcement Learning to Bridge the Gap between Simulation and Experiment in Energy Demand Response
Viaarxiv icon