Incremental Learning of Planning Actions in Model-Based Reinforcement Learning
Incremental Learning of Planning Actions in Model-Based Reinforcement Learning
复制标题
基于模型的强化学习中规划行动的增量学习
DOI：
10.24963/ijcai.2019/443
复制
发表时间：
2019
影响因子：
3.4
通讯作者：
Ronald P. A. Petrick
中科院分区：
文献类型：
--
作者：
Jun Hao Alvin Ng;Ronald P. A. Petrick
一个计划的合理性和最优性取决于领域模型的正确性。当智能体与其环境之间的交互很复杂时，指定完整的领域模型可能会很困难。我们提出一种基于模型的强化学习（MBRL）方法来解决模型未知的规划问题。该模型在多个情节中逐步学习，仅使用当前情节中的经验，这适合非平稳环境。我们引入可靠性这一新颖概念作为MBRL的内在动机，以及一种从失败中学习以防止类似失败重复出现的方法。我们的动机是提高MBRL的学习效率和目标导向性。我们通过三个规划领域的实验结果来评估我们的工作。
The soundness and optimality of a plan depends on the correctness of the domain model. Specifying complete domain models can be difficult when interactions between an agent and its environment are complex. We propose a model-based reinforcement learning (MBRL) approach to solve planning problems with unknown models. The model is learned incrementally over episodes using only experiences from the current episode which suits non-stationary environments. We introduce the novel concept of reliability as an intrinsic motivation for MBRL, and a method to learn from failure to prevent repeated instances of similar failures. Our motivation is to improve the learning efficiency and goal-directedness of MBRL. We evaluate our work with experimental results for three planning domains.