Tomáš Pevný

Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks.

2020 · arXiv (Cornell University)

We focus on reinforcement learning (RL) in relational problems that are naturally defined in terms of objects, their relations, and manipulations. These problems are characterized by variable state and action spaces, and finding a fixed-length …

When Should You Defend Your Classifier -- A Game-theoretical Analysis of Countermeasures against Adversarial Examples

2021 · arXiv (Cornell University)

Adversarial machine learning, i.e., increasing the robustness of machine learning algorithms against so-called adversarial examples, is now an established field. Yet, newly proposed methods are evaluated and compared under unrealistic scenarios where costs for adversary …

State Encodings for GNN-Based Lifted Planners

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

The application of graph neural networks (GNNs) to learn heuristic functions in classical planning is gaining traction. Despite the variety of methods proposed in the literature to encode classical planning tasks for GNNs, a comparative …