Multivariate nonlinear mixed-effects models(MNLMM) have seen an increasing use due to its flexibility for analyzing multi-outcome longitudinal data following nonlinear profiles. In this work, I present and compare fiv...
详细信息
Multivariate nonlinear mixed-effects models(MNLMM) have seen an increasing use due to its flexibility for analyzing multi-outcome longitudinal data following nonlinear profiles. In this work, I present and compare five different numerical algorithms for maximum likelihood estimation of the MNLMM. These algorithmic approaches include the penalized nonlinear least squares coupled with multivariate linear mixed-effects(PNLS-MLME) approximation, Laplacian approximation, pseudo-data ECM algorithm, Monte Carlo EM algorithm, and importance sampling EM algorithm. When estimating the MNLMM, it is rather difficult to exactly evaluate the observed log-likelihood function in a closed-form expression because it involves evaluating a multiple integral. Therefore, the corresponding approximations of the observed log-likelihood function under the five algorithms are presented. A comparison of their computational performances is investigated through simulation and real data from an AIDS clinical study.
Traditional multi-agent deep reinforcement learning has difficulty obtaining rewards,slow convergence,and effective cooperation among agents in the pretraining period due to the large joint state space and sparse rewa...
详细信息
Traditional multi-agent deep reinforcement learning has difficulty obtaining rewards,slow convergence,and effective cooperation among agents in the pretraining period due to the large joint state space and sparse rewards for ***,this paper discusses the role of demonstration data in multiagent systems and proposes a multi-agent deep reinforcement learning algorithm from fuse adaptive weight fusion demonstration *** algorithm sets the weights according to the performance and uses the importance sampling method to bridge the deviation in the mixed sampled data to combine the expert data obtained in the simulation environment with the distributed multi-agent reinforcement learning algorithm to solve the difficult *** problem of global exploration improves the convergence speed of the *** results in the RoboCup2D soccer simulation environment show that the algorithm improves the ability of the agent to hold and shoot the ball,enabling the agent to achieve a higher goal scoring rate and convergence speed relative to demonstration policies and mainstream multi-agent reinforcement learning algorithms.
暂无评论