Author name cluster

Tomáš Pevný

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

AAAI Conference 2025 Conference Paper

State Encodings for GNN-Based Lifted Planners

Rostislav Horčik
Gustav Šír
Vítězslav Šimek
Tomáš Pevný

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 study evaluating their relative performances has been lacking. Moreover, some encodings have been assessed solely for their expressiveness rather than practical effectiveness in planning. This paper provides an extensive comparative analysis of existing encodings. Our results indicate that the smallest encoding based on Gaifman graphs, not yet applied in planning, outperforms the rest due to its fast evaluation times and the informativeness of the resulting heuristic. The overall coverage measured on the IPC almost reaches that of the state-of-the-art planner LAMA while exhibiting rather complementary strengths across different domains.

PDF Details DOI

PRL Workshop 2022 Workshop Paper

Heuristic Search Planning with Deep Neural Networks using Imitation, Attention and Curriculum Learning

Leah Chrestien
Tomáš Pevný
Stefan Edelkamp
Antonín Komenda

Learning a well-informed heuristic function for hard planning domains is an elusive problem. Although there are known neural network architectures to represent such heuristic knowledge, it is not obvious what concrete information is learned and whether techniques aimed at understanding the structure help in improving the quality of the heuristics. This paper presents a network model that learns a heuristic function capable of relating distant parts of the state space via optimal plan imitation using the attention mechanism which drastically improves the learning of a good heuristic function. To counter the limitation of this method in the creation of problems of increasing difficulty, we demonstrate the use of curriculum learning, where newly solved problem instances are added to the training set, which, in turn, helps to solve problems of higher complexities and far exceeds the performances of all existing baselines including classical planning heuristics. We demonstrate its effectiveness on grid-type PDDL domains.

PDF Details

JMLR Journal 2022 Journal Article

JsonGrinder.jl: automated differentiable neural architecture for embedding arbitrary JSON data

Šimon Mandlík
Matěj Račinský
Viliam Lisý
Tomáš Pevný

Standard machine learning (ML) problems are formulated on data converted into a suitable tensor representation. However, there are data sources, for example in cybersecurity, that are naturally represented in a unifying hierarchical structure, such as XML, JSON, and Protocol Buffers. Converting this data to a tensor representation is usually done by manual feature engineering, which is laborious, lossy, and prone to bias originating from the human inability to correctly judge the importance of particular features. JsonGrinder.jl is a library automating various ML tasks on these difficult sources. Starting with an arbitrary set of JSON samples, it automatically creates a differentiable ML model (called hmilnet), which embeds raw JSON samples into a fixed-size tensor representation. This embedding network can be naturally extended by an arbitrary ML model expecting tensor inputs in order to perform classification, regression, or clustering. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2022. ( edit, beta )

PDF Details

PRL Workshop 2020 Workshop Paper

Model-free Automated Planning Using Neural Networks

Michaela Urbanovská
Jan Bím
Leah Chrestien
Antonín Komenda
Tomáš Pevný

Automated planning for problems without an explicit model is an elusive research challenge, which, however, if tackled, could provide general approach to problems in real-world unstructured environments. There are currently two strong research directions in the area of Artificial Intelligence (AI), namely, machine learning and symbolic AI. The former provides techniques to learn models of unstructured data but does not provide further problem solving capabilities on such models. The latter provides efficient algorithms for general problem solving, but requires a model to work with. In this paper, we propose a combination of these two areas, namely deep learning and classical planning, to form a planning system that works without a human-encoded model. The deep learning part extracts the model in a form of a transition system and a goal-distance heuristic estimator; the classical planning part uses such a model to efficiently solve the planning problem. Besides the design of such planning systems, we provide experimental evaluations comparing the implemented technique to classical model-based methods.

PDF Details

AAAI Conference 2019 Conference Paper

Classification with Costly Features Using Deep Reinforcement Learning

Jaromír Janisch
Tomáš Pevný
Viliam Lisý

We study a classification problem where each feature can be acquired for a cost and the goal is to optimize a trade-off between the expected classification error and the feature cost. We revisit a former approach that has framed the problem as a sequential decision-making problem and solved it by Q-learning with a linear approximation, where individual actions are either requests for feature values or terminate the episode by providing a classification decision. On a set of eight problems, we demonstrate that by replacing the linear approximation with neural networks the approach becomes comparable to the state-of-the-art algorithms developed specifically for this problem. The approach is flexible, as it can be improved with any new reinforcement learning enhancement, it allows inclusion of pre-trained high-performance classifier, and unlike prior art, its performance is robust across all evaluated datasets.

PDF Details