论文标题
与状态聚集的无模型情节控制
Model-Free Episodic Control with State Aggregation
论文作者
论文摘要
情节控制提供了一种高度样本效率的方法，用于增强学习，同时执行高内存和计算要求。这项工作提出了一种简单的启发式方法来减少这些要求，并提出了无模型的情节控制（MFEC）的应用。 Atari Games的实验表明，这种启发式方法成功地减少了MFEC计算需求，同时使用保守的超参数选择时不会产生明显的性能丧失。因此，在处理强化学习任务时，情节控制成为更可行的选择。
Episodic control provides a highly sample-efficient method for reinforcement learning while enforcing high memory and computational requirements. This work proposes a simple heuristic for reducing these requirements, and an application to Model-Free Episodic Control (MFEC) is presented. Experiments on Atari games show that this heuristic successfully reduces MFEC computational demands while producing no significant loss of performance when conservative choices of hyperparameters are used. Consequently, episodic control becomes a more feasible option when dealing with reinforcement learning tasks.
