Jakub Grudzien Kuba

multi-agent reinforcement learning (2) black-box optimization (1) policy gradient (1) nash equilibrium (1) variance reduction (1) distribution shift (1) optimal baseline (1) convergence guarantee (1) gradient estimator (1) heterogeneous agent (1) model-based optimization (1) functional graphical model (1) monotonic improvement (1) mirror learning (1) multi-agent policy gradient (1) heterogeneous-agent reinforcement learning (1) advantage decomposition (1) trust region learning (1) transformer architecture (1) baseline function (1)