4 papers
Learning General Policies with Policy Gradient Methods
Simon Ståhlberg, Blai Bonet, Hector Geffner
While reinforcement learning methods have delivered remarkable results in a number of settings, generalization, i.e., the ability to produce policies that generalize in a reliable…
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 More Expressive General Policies for Classical Planning Domains
Simon Ståhlberg, Blai Bonet, Hector Geffner
GNN-based approaches for learning general policies across planning domains are limited by the expressive power of , namely; first-order logic with two variables and counting.…
Learning to Ground Existentially Quantified Goals
Martin Funkquist, Simon Ståhlberg, Hector Geffner
Goal instructions for autonomous AI agents cannot assume that objects have unique names. Instead, objects in goals must be referred to by providing suitable descriptions. However,…