PEORL swMATH ID: 29437 Software Authors: Fangkai Yang, Daoming Lyu, Bo Liu, Steven Gustafson Description: PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making. Reinforcement learning and symbolic planning have both been used to build intelligent autonomous agents. Reinforcement learning relies on learning from interactions with real world, which often requires an unfeasibly large amount of experience. Symbolic planning relies on manually crafted symbolic knowledge, which may not be robust to domain uncertainties and changes. In this paper we present a unified framework {em PEORL} that integrates symbolic planning with hierarchical reinforcement learning (HRL) to cope with decision-making in a dynamic environment with uncertainties. Symbolic plans are used to guide the agent’s task execution and learning, and the learned experience is fed back to symbolic knowledge to improve planning. This method leads to rapid policy search and robust symbolic plans in complex domains. The framework is tested on benchmark domains of HRL. Homepage: https://arxiv.org/abs/1804.07779 Keywords: Machine Learning: arXiv_cs.LG; Artificial Intelligence; arXiv_cs.AI; arXiv_stat.ML; PEORL framework Related Software: REBA; BWIBots; ALM; CCalc; PDDL; Clingcon; DeepProbLog; DL2; FODD-Planner; Smodels; BLOG; Clingo Cited in: 5 Publications Standard Articles 1 Publication describing the Software Year PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making Fangkai Yang, Daoming Lyu, Bo Liu, Steven Gustafson 2018 all top 5 Cited by 13 Authors 2 Lee, Joohyung 2 Wang, Yi 2 Zhang, Shiqi 1 Eberhart, Aaron 1 Gelfond, Michael 1 Gustafson, Steven M. 1 Hitzler, Pascal 1 Liu, Bo 1 Lyu, Daoming 1 Sarker, Md Kamruzzaman 1 Sridharan, Mohan 1 Yang, Fangkai 1 Zhou, Lu Cited in 3 Serials 2 Theory and Practice of Logic Programming 1 AI Communications 1 The Journal of Artificial Intelligence Research (JAIR) Cited in 1 Field 5 Computer science (68-XX) Citations by Year