This paper addresses the prediction stability, prediction accuracy and
control capability of the current probabilistic model-based reinforcement
learning (MBRL) built on neural networks. A novel approach dropout-based
probabilistic ensembles with trajectory sampling (DPETS) is proposed where the
system uncertainty is stably predicted by combining the Monte-Carlo dropout and
trajectory sampling in one framework. Its loss function is designed to correct
the fitting error of neural networks for more accurate prediction of
probabilistic models. The state propagation in its policy is extended to filter
the aleatoric uncertainty for superior control capability. Evaluated by several
Mujoco benchmark control tasks under additional disturbances and one practical
robot arm manipulation task, DPETS outperforms related MBRL approaches in both
average return and convergence velocity while achieving superior performance
than well-known model-free baselines with significant sample efficiency. The
open source code of DPETS is available at this https URL

本研究提出了一种基于神经网络的概率模型强化学习方法，利用 Monte-Carlo dropout 和轨迹采样相结合的 DPETS 框架来稳定预测系统不确定性，并通过设计适应神经网络拟合误差的损失函数实现更准确的概率模型预测。在评估中，DPETS 在多个控制任务中表现优于相关 MBRL 方法和无模型基准，并实现了显著的样本效率提高。