Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinement
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Inductive Collaborative Filtering via Relation Graph Learning
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+1Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning
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
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 CompletionBeyond Interpolation: Extrapolative Reasoning with Reinforcement Learning and Graph Neural Networks
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 BiasGraph Neural Networks for Image Classification and Reinforcement Learning using Graph representations
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