A3C ArrayOutOfBounds

问题描述

每次调用 A3CdiscreteDense().train() 时都会出错；

Exception in thread "Thread-7" java.lang.Arrayindexoutofboundsexception: -1
    at java.util.ArrayList.elementData(UnkNown Source)
    at java.util.ArrayList.get(UnkNown Source)
    at org.deeplearning4j.rl4j.learning.async.a3c.discrete.AdvantageActorCriticUpdatealgorithm.computeGradients(AdvantageActorCriticUpdatealgorithm.java:63)
    at org.deeplearning4j.rl4j.learning.async.a3c.discrete.AdvantageActorCriticUpdatealgorithm.computeGradients(AdvantageActorCriticUpdatealgorithm.java:32)
    at org.deeplearning4j.rl4j.learning.async.AsyncThreaddiscrete.trainSubEpoch(AsyncThreaddiscrete.java:130)
    at org.deeplearning4j.rl4j.learning.async.AsyncThread.handleTraining(AsyncThread.java:192)
    at org.deeplearning4j.rl4j.learning.async.AsyncThread.run(AsyncThread.java:168)

但是当我使用 DQN 时，相同的代码可以正常工作。

解决方法

我遇到了同样的问题。似乎默认学习配置不起作用，因为 nStep 值不应为 0。从构建器创建学习配置时只需调用 .nStep(5)。您可以在此处找到更多信息：https://github.com/eclipse/deeplearning4j-examples/issues/991#issuecomment-823133909

deeplearning4j dl4j java java