The benchmarks from previous International Planning Competitions (IPCs) are the de-facto
standard for evaluating planning algorithms. The IPC set is both a collection of planning …

We study how group symmetry helps improve data efficiency and generalization for end-to-
end differentiable planning algorithms when symmetry appears in decision-making tasks …

In this planner abstract, we introduce the version of the Powerlifted (Corrêa et al. 2020)
planning system used in the IPC 2023. Powerlifted is a lifted planner that works directly on …

Potential heuristics assign a numerical value (potential) to each fact and compute the
heuristic value for a given state as the sum of these potentials. A mutex is an invariant stating …

Classical planning tasks are usually modelled in the PDDL which is a schematic language
based on first-order logic. Nevertheless, most of the current planners turn this first-order …

Reinforcement learning (RL) algorithms for continuous control tasks require accurate
sampling-based action selection. Many tasks, such as robotic manipulation, contain inherent …

Agents operating in a multi-agent environment must consider not just their actions, but also
those of the other agents in the system. Artificial social systems are a well-known means for …

Symmetry-based pruning is a powerful method for reducing the search effort in finitedomain
planning. This method is based on exploiting an automorphism group connected to the …

HUZAR: Predicting Useful Actions with Graph Neural Networks Page 1 HUZAR: Predicting
Useful Actions with Graph Neural Networks Piotr Rafał Gzubicki, Bartosz Piotr Lachowicz, Alvaro …

A general-purpose agent must learn an open-scope world model: one rich enough to tackle
any of the wide range of tasks it may be asked to solve over its operational lifetime. This …