AdversarialIntrinsicMotivationforReinforcement Learning

Neural Information Processing Systems 

In thispaper,weinvestigatewhether onesuchobjective,theWasserstein-1 distance between a policy's state visitation distribution and a target distribution, can be utilized effectivelyforreinforcement learning (RL)tasks.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found