Pallab Dasgupta

safe reinforcement learning (2) constraint satisfaction (2) policy optimization (2) reinforcement learning (1) constraint optimization (1) constrained reinforcement learning (1) bayesian optimization (1) reward maximization (1) filtering approach (1) safety constraint (1) sparse network (1) gradient-based update (1) non-parametric method (1) glottal closure instant (1) speech signal processing (1) voice analysis (1) policy refinement (1) penalty method (1) penalty barrier method (1) safety specification (1)