7 papers
Safety from Honesty in a Disinterested AI Predictor
Yoshua Bengio, Oliver Richardson, Tomáš GavenÄiak +13
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified…
SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration
Kaustubh Mani, Yann Pequignot, Vincent Mai +1
Safe exploration is a prerequisite for deploying reinforcement learning (RL) agents in safety-critical domains. In this paper, we approach safe exploration through the lens of epis…
Shielded Controller Units for RL with Operational Constraints Applied to Remote Microgrids
Hadi Nekoei, Alexandre Blondin Massé, Rachid Hassani +2
Reinforcement learning (RL) is a powerful framework for optimizing decision-making in complex systems under uncertainty, an essential challenge in real-world settings, particularly…
Active Learning-Based Optimization of Hydroelectric Turbine Startup to Minimize Fatigue Damage
Vincent Mai, Quang Hung Pham, Arthur Favrel +2
Hydro-generating units (HGUs) play a crucial role in integrating intermittent renewable energy sources into the power grid due to their flexible operational capabilities. This evol…
Safety Representations for Safer Policy Learning
Kaustubh Mani, Vincent Mai, Charlie Gauthier +3
Reinforcement learning algorithms typically necessitate extensive exploration of the state space to find optimal policies. However, in safety-critical applications, the risks assoc…
Accelerating Quasi-Static Time Series Simulations with Foundation Models
Alban Puech, François Mirallès, Jonas Weiss +5
Quasi-static time series (QSTS) simulations have great potential for evaluating the grid's ability to accommodate the large-scale integration of distributed energy resources. Howev…