Dongho Kim

offline reinforcement learning (1) policy optimization (1) variational inference (1) bayesian reinforcement learning (1) function approximation (1) hyperparameter optimization (1) distributed learning (1) distributed optimization (1) model-based reinforcement learning (1) batch reinforcement learning (1) off-policy learning (1) cost-sensitive exploration (1) constrained markov decision process (1) model-based brl (1) exploration constraints (1) exploration policy (1) consensus optimization (1) physics-informed neural network (1) inductive bia (1) quadratic convergence (1)