资源论文Playing FPS Games With Environment-Aware Hierarchical Reinforcement Learning

Playing FPS Games With Environment-Aware Hierarchical Reinforcement Learning

2019-10-09 | |  202 |   58 |   0

Abstract Learning rational behaviors in First-person-shooter (FPS) games is a challenging task for Reinforcement Learning (RL) with the primary diffificulties of huge action space and insuffificient exploration. To address this, we propose a hierarchical agent based on combined options with intrinsic rewards to drive exploration. Specififically, we present a hierarchical model that works in a manager-worker fashion over two levels of hierarchy. The highlevel manager learns a policy over options, and the low-level workers, motivated by intrinsic reward, learn to execute the options. Performance is further improved with environmental signals appropriately harnessed. Extensive experiments demonstrate that our trained bot signifificantly outperforms the alternative RL-based models on FPS games requiring maze solving and combat skills, etc. Notably, we achieved fifirst place in VDAIC 2018 Track(1)

上一篇:Meta Reinforcement Learning with Task Embedding and Shared Policy

下一篇:Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning

用户评价
全部评价

热门资源

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Rating-Boosted La...

    The performance of a recommendation system reli...

  • Hierarchical Task...

    We extend hierarchical task network planning wi...