RePReL: Integrating Relational Planning and Reinforcement Learning for Effective Abstraction
| Reinforcement Learning Planning Relational MDP Hierarchical |
PaperID: 55
pdf
poster
|
| 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. | |
Session 13: Temporal Planning | Numeric Planning | Reinforcement Learning
RePReL: Integrating Relational Planning and Reinforcement Learning for Effective Abstraction
Authors: Harsha Kokel, Arjun Manoharan, Sriraam Natarajan, Balaraman Ravindran and Prasad Tadepalli
Keywords:
Reinforcement LearningPlanningRelational MDPHierarchical
LM-cut and Operator Counting Heuristics for Optimal Numeric Planning with Simple Conditions
Authors: Ryo Kuroiwa, Alexander Shleyfman, Chiara Piacentini, Margarita Castro and J. Christopher Beck
Keywords:
numeric planningheuristic searchoptimal planningLM-cutplanning with resourcesoperator-counting
Privacy-Preserving Algorithm for Decoupling of Multi-Agent Plans with Uncertainty
Authors: Yuening Zhang and Brian Williams
Keywords:
temporal networktemporal decouplingmulti-agent systemsmulti-agent scheduling and executionprivacy
Blind Decision Making: Reinforcement Learning with Delayed Observations
Authors: Mridul Agarwal and Vaneet Aggarwal
Keywords:
Reinforcement LearningDelayed Reinforcement LearningPlanning and Control