RePReL: Integrating Relational Planning and Reinforcement Learning for Effective Abstraction
RePReL: Integrating Relational Planning and Reinforcement Learning for Effective Abstraction
复制标题
RePReL:集成关系规划和强化学习以实现有效抽象
DOI:
10.1609/icaps.v31i1.16001
复制
发表时间:
2021
影响因子:
4
通讯作者:
Prasad Tadepalli
中科院分区:
文献类型:
--
作者:
Harsha Kokel;Arjun Manoharan;Sriraam Natarajan;Balaraman Ravindran;Prasad Tadepalli
State abstraction is necessary for better task transfer in complex reinforcement learning environments. Inspired by the benefit of state abstraction in MAXQ and building upon hybrid planner-RL architectures, we propose RePReL, a hierarchical framework that leverages a relational planner to provide useful state abstractions. Our experiments demonstrate that the abstractions enable faster learning and efficient transfer across tasks. More importantly, our framework enables the application of standard RL approaches for learning in structured domains. The benefit of using the state abstractions is critical in relational settings, where the number and/or types of objects are not fixed apriori. Our experiments clearly show that RePReL framework not only achieves better performance and efficient learning on the task at hand but also demonstrates better generalization to unseen tasks.
DOI:
--
发表时间:
2018-07
期刊:
--
影响因子:
--
作者:
David Abel;Dilip Arumugam;Lucas Lehnert;M. Littman
通讯作者:
David Abel;Dilip Arumugam;Lucas Lehnert;M. Littman