• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Adaptive Behavior >Affect, Anticipation, and Adaptation: Affect-Controlled Selection of Anticipatory Simulation in Artificial Adaptive Agents
【24h】

Affect, Anticipation, and Adaptation: Affect-Controlled Selection of Anticipatory Simulation in Artificial Adaptive Agents

机译：影响，预期和适应：人工自适应代理中预期模拟的影响控制选择

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Emotion plays an important role in thinking. In this article we study affective control of the amount of simulated anticipatory behavior in adaptive agents using a computational model. Our approach is based on model-based reinforcement learning (RL) and inspired by the simulation hypothesis (Cotterill, 2001; Hesslow, 2002). The simulation hypothesis states that thinking is internal simulation of behavior using the same sensory-motor systems as those used for overt behavior. Here, we study the adaptive-ness of an artificial agent, when action-selection bias is induced by an affect-controlled amount of simulated anticipatory behavior. To this end, we introduce an affect-controlled simulation-selection mechanism that uses the predictions of the agent's RL model to select anticipatory behaviors for simulation. Based on experiments with adaptive agents in two nondeterministic partially observable grid-worlds we conclude that (1) internal simulation has an adaptive benefit and (2) affective control can reduce the amount of simulation needed for this benefit. This is specifically the case if the following relation holds: positive affect decreases the amount of simulation towards simulating the best potential next action, while negative affect increases the amount of simulation towards simulating all potential next actions. In essence we use artificial affect to control mental exploration versus exploitations. Thus, agents "feeling positive" can think ahead in a narrow sense and free up working memory resources, while agents "feeling negative" must think ahead in a broad sense and maximize usage of working memory. Our results are consistent with several psychological findings on the relation between affect and learning, and contribute to answering the question of when positive versus negative affect is useful during adaptation.
机译：情绪在思考中起着重要作用。在本文中，我们使用计算模型研究自适应代理中模拟预期行为量的情感控制。我们的方法基于基于模型的强化学习（RL），并受到模拟假设的启发（Cotterill，2001； Hesslow，2002）。模拟假设指出，思维是行为的内部模拟，它使用与公开行为相同的感觉运动系统。在这里，当行为选择偏差是由情感控制量的模拟预期行为引起的时，我们研究人工代理的适应性。为此，我们引入了一种情感控制的模拟选择机制，该机制使用主体的RL模型的预测来选择预期行为进行模拟。基于在两个不确定的部分可观察的网格世界中使用自适应代理进行的实验，我们得出结论：（1）内部仿真具有自适应优势，而（2）情感控制可以减少为此优势所需的仿真数量。如果满足以下关系，则尤其是这种情况：正面影响会减少模拟量，以模拟最佳的潜在下一个动作，而负面影响会增加模拟量，以模拟所有可能的下一个动作。本质上，我们使用人为的情感来控制精神探索与剥削。因此，代理“感觉良好”可以从狭义上考虑并释放工作内存资源，而代理“感觉否定”必须从广义上考虑并最大化使用工作内存。我们的结果与关于情感与学习之间关系的一些心理学发现是一致的，并且有助于回答在适应过程中何时积极与消极的情感有用的问题。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号