Cosmin Paduraru

reinforcement learning (1) off-policy evaluation (1) offline reinforcement learning (1) policy optimization (1) policy learning (1) sequential decision (1) policy selection (1) directed graph (1) bayesian optimization (1) positional encoding (1) continuous action (1) discrete action (1) kernel function (1) offline policy selection (1) state distribution (1) graph neural network (1) magnetic laplacian (1)