arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.08960cs.LG
收藏

即插即用,基于模型的强化学习

Plug and Play, Model-Based Reinforcement Learning

Applied Artificial Intelligence Institute ( A 2I 2 ), Deakin Uni-versity, Geelong, Australia

Majid Abdolshah, Hung Le, Thommen Karimpanal George, Sunil Gupta, Santu Rana, Svetha Venkatesh

摘要:

强化学习方法的样本有效推广一直是一个挑战,特别是对于具有许多组件的复杂场景。在这项工作中,我们引入即插即用马尔可夫决策过程,一个基于对象的表示,允许zero-shot集成新的对象从已知的对象类。这是通过将全局过渡动态表示为局部过渡函数的联合来实现的,每个局部过渡函数相对于场景中的一个活动对象。对象类的转换动态可以预先学习,因此可以在新环境中使用。每一个活动对象也被赋予了奖励功能。由于没有中央奖励函数,因此可以通过仅更新所涉及对象的奖励函数来有效地处理对象的添加或移除。提出了一种新的迁移学习机制来适应这种情况下的奖励函数。实验表明,我们的表示可以实现在各种设置的样本效率。

英文摘要:

Sample-efficient generalisation of reinforcement learning approaches have always been a challenge, especially, for complex scenes with many components. In this work, we introduce Plug and Play Markov Decision Processes, an object-based representation that allows zero-shot integration of new objects from known object classes. This is achieved by representing the global transition dynamics as a union of local transition functions, each with respect to one active object in the scene. Transition dynamics from an object class can be pre-learnt and thus would be ready to use in a new environment. Each active object is also endowed with its reward function. Since there is no central reward function, addition or removal of objects can be handled efficiently by only updating the reward functions of objects involved. A new transfer learning mechanism is also proposed to adapt reward function in such cases. Experiments show that our representation can achieve sample-efficiency in a variety of set-ups.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑