1 citations · 2 across the 9 of their papers we have counts for
10 papers
Data-Driven MPC with Adaptively Sampled Non-Expert Demonstrations: Performance Guarantees and Sample Complexity
Shijie Pan, Agustin Castellano, Enrique Mallada
We study data-driven policy construction for dynamical systems using trajectories generated by surrogate finite-horizon Model Predictive Control (MPC), with the goal of approximati…
Memory-Computation Tradeoffs in Semi Amortized Parametric Optimization
Shijie Pan, Agustin Castellano, Zeyu Shen +1
Learning-enabled decision systems often use offline data or computation to reduce online compute cost. Despite the empirical success of such approaches, there is limited general un…
Learning Reachability of Energy Storage Arbitrage
Tomás Tapia, Agustin Castellano, Enrique Mallada +1
Power systems face increasing weather-driven variability and, therefore, increasingly rely on flexible but energy-limited storage resources. Energy storage can buffer this variabil…
Data-driven Acceleration of MPC with Guarantees
Agustin Castellano, Shijie Pan, Enrique Mallada
Model Predictive Control (MPC) is a powerful framework for optimal control but can be too slow for low-latency applications. We present a data-driven framework to accelerate MPC by…
Learning safety critics via a non-contractive binary bellman operator
Agustin Castellano, Hancheng Min, Juan Andrés Bazerque +1
The inability to naturally enforce safety in Reinforcement Learning (RL), with limited failures, is a core challenge impeding its use in real-world applications. One notion of safe…
Reinforcement Learning with Almost Sure Constraints
Agustin Castellano, Hancheng Min, Juan Bazerque +1
In this work we address the problem of finding feasible policies for Constrained Markov Decision Processes under probability one constraints. We argue that stationary policies are…
Learning to Act Safely with Limited Exposure and Almost Sure Certainty
Agustin Castellano, Hancheng Min, Juan Bazerque +1
This paper puts forward the concept that learning to take safe actions in unknown environments, even with probability one guarantees, can be achieved without the need for an unboun…
Assured RL: Reinforcement Learning with Almost Sure Constraints
Agustin Castellano, Juan Bazerque, Enrique Mallada
We consider the problem of finding optimal policies for a Markov Decision Process with almost sure constraints on state transitions and action triplets. We define value and action-…
Quadratic approximate dynamic programming for scheduling water resources: a case study
Agustin Castellano, Camila Martínez, Pablo Monzón +3
We address the problem of scheduling water resources in a power system via approximate dynamic programming.To this goal, we model a finite horizon economic dispatch problemwith con…
Learning to be safe, in finite time
Agustin Castellano, Juan Bazerque, Enrique Mallada
This paper aims to put forward the concept that learning to take safe actions in unknown environments, even with probability one guarantees, can be achieved without the need for an…