paper-with-me

홈 › Papers

Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinement

2025-09-11 · Jakob Nyberg, Pontus Johnson arxiv

We present and evaluate Vejde; a framework which combines data abstraction, graph neural networks and reinforcement learning to produce inductive policy functions for decision problems with richly structured states, such as object classes and relations. MDP states are represented as data bases of facts about entities, and Vejde converts each state to a bipartite graph, which is mapped to latent states through neural message passing. The factored representation of both states and actions allows Vejde agents to handle problems of varying size and structure. We tested Vejde agents on eight problem domains defined in RDDL, with ten problem instances each, where policies were trained using both supervised and reinforcement learning. To test policy generalization, we separate problem instances in two sets, one for training and the other solely for testing. Test results on unseen instances for the Vejde agents were compared to MLP agents trained on each problem instance, as well as the online planning algorithm Prost. Our results show that Vejde policies in average generalize to the test instances without a significant loss in score. Additionally, the inductive agents received scores on unseen test instances that on average were close to the instance-specific MLP agents.

📄 PDF Abstract BibTeX arXiv:2509.09219

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Inductive Collaborative Filtering via Relation Graph Learning

2021-01-01 · Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Hongyuan Zha

Collaborative filtering has shown great power in predicting potential user-item ratings by factorizing an observed user-item rating matrix into products of two sets of latent factors. However, the user-specific latent fa…

Collaborative FilteringGraph LearningInductive LearningMatrix Completion+1

Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning

2021-02-08 · Zhengyao Jiang, Pasquale Minervini, Minqi Jiang, Tim Rocktaschel

Although reinforcement learning has been successfully applied in many domains in recent years, we still lack agents that can systematically generalize. While relational inductive biases that fit a task can improve genera…

reinforcement-learningReinforcement Learning (RL)

ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective

2022-07-20 · Yihong Chen, Pushkar Mishra, Luca Franceschi, Pasquale Minervini 외

Factorisation-based Models (FMs), such as DistMult, have enjoyed enduring success for Knowledge Graph Completion (KGC) tasks, often outperforming Graph Neural Networks (GNNs). However, unlike GNNs, FMs struggle to incorp…

Knowledge Graph Completion

Beyond Interpolation: Extrapolative Reasoning with Reinforcement Learning and Graph Neural Networks

2025-02-06 · Niccolò Grillo, Andrea Toccaceli, Joël Mathys, Benjamin Estermann 외

Despite incredible progress, many neural architectures fail to properly generalize beyond their training distribution. As such, learning to reason in a correct and generalizable way is one of the current fundamental chal…

Inductive Bias

Graph Neural Networks for Image Classification and Reinforcement Learning using Graph representations

2022-03-07 · Naman Goyal, David Steiner

In this paper, we will evaluate the performance of graph neural networks in two distinct domains: computer vision and reinforcement learning. In the computer vision section, we seek to learn whether a novel non-redundant…

image-classificationImage ClassificationInductive Biasreinforcement-learning+3