4 papers
Certifiable Safe Model-Based Reinforcement Learning with Control-Affine Dynamics Approximation
Hao Zhou, Yanze Zhang, Cameron Reid +1
Safe model-based reinforcement learning (RL) often bridges control-theoretic analysis and RL for robots to safely explore (partially) unknown system dynamics while deriving control…
A Mathematical Theory of Agency and Intelligence
Wael Hafez, Chenan Wei, Rodrigo Pena +2
To operate reliably under changing conditions, complex systems require feedback on how effectively they use resources, not just whether objectives are met. Current AI systems proce…
The Informational Cost of Agency: A Bounded Measure of Interaction Efficiency for Deployed Reinforcement Learning
Wael Hafez, Cameron Reid, Amit Nazeri
Deployed reinforcement learning systems lack a principled runtime reliability theory. We close this gap by introducing Bipredictability, P, a closed form information theoretic metr…
Mutual Information Tracks Policy Coherence in Reinforcement Learning
Cameron Reid, Wael Hafez, Amirhossein Nazeri
Reinforcement Learning (RL) agents deployed in real-world environments face degradation from sensor faults, actuator wear, and environmental shifts, yet lack intrinsic mechanisms t…