Constrained Model-Free Reinforcement Learning for Process Optimization

no code implementations • 16 Nov 2020 • Elton Pan, Panagiotis Petsagkourakis, Max Mowbray, Dongda Zhang, Antonio del Rio-Chanona

We propose an 'oracle'-assisted constrained Q-learning algorithm that guarantees the satisfaction of joint chance constraints with a high probability, which is crucial for safety critical tasks.

Model Predictive Control Q-Learning +3