Dzhivelikian Evgenii, Latyshev Artem, Kuderov Petr, Panov Aleksandr I
Moscow Institute of Physics and Technology, Dolgoprudny, Russia.
Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences, Moscow, Russia.
Brain Inform. 2022 Apr 2;9(1):8. doi: 10.1186/s40708-022-00156-6.
Biologically plausible models of learning may provide a crucial insight for building autonomous intelligent agents capable of performing a wide range of tasks. In this work, we propose a hierarchical model of an agent operating in an unfamiliar environment driven by a reinforcement signal. We use temporal memory to learn sparse distributed representation of state-actions and the basal ganglia model to learn effective action policy on different levels of abstraction. The learned model of the environment is utilized to generate an intrinsic motivation signal, which drives the agent in the absence of the extrinsic signal, and through acting in imagination, which we call dreaming. We demonstrate that the proposed architecture enables an agent to effectively reach goals in grid environments.
具有生物学合理性的学习模型可能为构建能够执行广泛任务的自主智能体提供关键见解。在这项工作中，我们提出了一个在强化信号驱动下在陌生环境中运行的智能体分层模型。我们使用时间记忆来学习状态-动作的稀疏分布式表示，并使用基底神经节模型在不同抽象层次上学习有效的动作策略。所学习的环境模型用于生成内在动机信号，该信号在没有外在信号时驱动智能体，并通过在想象中行动，我们称之为做梦。我们证明所提出的架构能够使智能体在网格环境中有效地实现目标。
