4 papers
First-Order Representation Languages for Goal-Conditioned RL
Simon Ståhlberg, Hector Geffner
First-order relational languages have been used in MDP planning and reinforcement learning (RL) for two main purposes: specifying MDPs in compact form, and representing and learnin…
Learning Lifted Action Models From Traces of Incomplete Actions and States
Niklas Jansen, Jonas Gösgens, Hector Geffner
Consider the problem of learning a lifted STRIPS model of the sliding-tile puzzle from random state-action traces where the states represent the location of the tiles only, and the…
Sketch Decompositions for Classical Planning via Deep Reinforcement Learning
Michael Aichmüller, Hector Geffner
In planning and reinforcement learning, the identification of common subgoal structures across problems is important when goals are to be achieved over long horizons. Recently, it…
Learning Lifted STRIPS Models from Action Traces Alone: A Simple, General, and Scalable Solution
Jonas Gösgens, Niklas Jansen, Hector Geffner
Learning STRIPS action models from action traces alone is a challenging problem as it involves learning the domain predicates as well. In this work, a novel approach is introduced…