首页> 外文会议>Ninth International Conference on Machine Learning and Applications >Enhancing Inference in Relational Reinforcement Learning Via Truth Maintenance Systems
【24h】

Enhancing Inference in Relational Reinforcement Learning Via Truth Maintenance Systems

机译:通过真相维护系统增强关系强化学习中的推理

获取原文

摘要

Computational complexity is still a challenging problem for intelligent systems operating in compound environments. To tackle it, an agent has to deal with perceptual information intelligently. In this paper, we propose an efficient and adaptive reasoning system based on Adaptive Logic Interpreter reasoning system, a mechanism for guiding inference through relational reinforcement learning, and a variation of Truth Maintenance Systems to speed up the inference. Relational reinforcement learning guides the inference toward the most rewarding parts of the knowledge base and truth maintenance system maintains beliefs, avoids repetitive inferences and reduces the state space. Empirical results demonstrate higher performance than the basic approach in terms of number of inferred instances, average reward, and average reward accuracy.
机译:对于在复合环境中运行的智能系统而言,计算复杂度仍然是一个具有挑战性的问题。为了解决这个问题,代理必须智能地处理感知信息。在本文中,我们提出了一种基于自适应逻辑解释器推理系统的高效自适应推理系统,一种通过关系强化学习指导推理的机制,以及一种变体维护系统以加快推理速度。关系强化学习将推理推向知识库中最有价值的部分,而真相维护系统则维护信念,避免重复推理并减少状态空间。从推断实例的数量,平均奖励和平均奖励准确性的角度来看,经验结果表明,与基本方法相比,该方法具有更高的性能。

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