结构化和非结构化环境中长形式强化学习的微观发生学解释。
A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments.
作者信息
Dyson Benjamin James, Asad Ahad
机构信息
University of Alberta, Edmonton, AB, Canada.
University of Sussex, Falmer, UK.
出版信息
NPJ Sci Learn. 2021 Jun 23;6(1):19. doi: 10.1038/s41539-021-00098-4.
We explored the possibility that in order for longer-form expressions of reinforcement learning (win-calmness, loss-restlessness) to manifest across tasks, they must first develop because of micro-transactions within tasks. We found no evidence of win-calmness or loss-restlessness when wins could not be maximised (unexploitable opponents), nor when the threat of win minimisation was presented (exploiting opponents), but evidence of win-calmness (but not loss-restlessness) when wins could be maximised (exploitable opponents).
我们探讨了一种可能性，即强化学习的较长形式表达（赢时平静、输时不安）要在各种任务中体现出来，首先必须因任务中的微观交易而发展起来。当无法实现获胜最大化时（不可利用的对手），以及当出现获胜最小化的威胁时（利用对手），我们没有发现赢时平静或输时不安的证据，但当可以实现获胜最大化时（可利用的对手），我们发现了赢时平静（但没有输时不安）的证据。
Zotero 插件