Data to 7 Oct 2026

Relational Deep Reinforcement Learning

arXiv 1806.01830 ↗First posted 5 Jun 2018cs.LG stat.MLcited by 72

Not on the map. Why?

Abstract (arXiv)

We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning. It uses self-attention to iteratively reason about the relations between entities in a scene and to guide a model-free policy. Our results show that in a novel navigation and planning task called Box-World, our agent finds interpretable solutions that improve upon baselines in terms of sample complexity, ability to generalize to more complex scenes than experienced during training, and overall performance. In the StarCraft II Learning Environment, our agent achieves state-of-the-art performance on six mini-games -- surpassing human grandmaster performance on four. By considering architectural inductive biases, our work opens new directions for overcoming important, but stubborn, challenges in deep RL.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 14; 2023: 16; 2024: 12; 2025: 6; 2026: 2.

72 papers.

Sort:

By area:

2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
2021Acquisition of Chess Knowledge in AlphaZerocited by 120
2021Object-Region Video Transformerscited by 73
2023A Survey of Temporal Credit Assignment in Deep Reinforcement Learningcited by 56
2024Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstructioncited by 51
2023A Survey on Transformers in Reinforcement Learningcited by 50
2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstractioncited by 45
2021Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planningcited by 43
2023Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZerocited by 41
2023Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphscited by 39
2021Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Trackingcited by 35

38 more

2021Procedural Generalization by Planning with Self-Supervised World Modelscited by 30
2022Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applicationscited by 27
2022Policy Architectures for Compositional Generalization in Controlcited by 23
2021Learning Efficient Multi-Agent Cooperative Visual Explorationcited by 19
2022Compositional Multi-Object Reinforcement Learning with Linear Relation Networkscited by 19
2023Systematic Visual Reasoning through Object-Centric Relational Abstractioncited by 19
2023Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Explorationcited by 17
2021Learning to Optimize Industry-Scale Dynamic Pickup and Delivery Problemscited by 15
2023Hierarchical Imitation Learning with Vector Quantized Modelscited by 15
2023Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approachcited by 15
2022On Efficient Reinforcement Learning for Full-length Game of StarCraft IIcited by 14
2022PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Datacited by 14
2024Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Modelscited by 14
2021High-Accuracy Model-Based Reinforcement Learning, a Surveycited by 13
2022A Survey on Reinforcement Learning Methods in Character Animationcited by 12
2021Neuro-Symbolic Constraint Programming for Structured Predictioncited by 11
2022Explainability in reinforcement learning: perspective and positioncited by 11
2022Learn the Time to Learn: Replay Scheduling in Continual Learningcited by 11
2021Phy-Q as a measure for physical reasoning intelligencecited by 10
2024Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learningcited by 10
2021Learning Symbolic Rules for Interpretable Deep Reinforcement Learningcited by 9
2023Benchmarks for Physical Reasoning AIcited by 8
2021Detecting and Adapting to Novelty in Gamescited by 7
2021Agent-Centric Representations for Multi-Agent Reinforcement Learningcited by 6
2021Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learningcited by 6
2023Hybrid Search for Efficient Planning with Completeness Guaranteescited by 6
2021Topos and Stacks of Deep Neural Networkscited by 5
2023Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Surveycited by 5
2024Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidencecited by 5
2024Temporal Knowledge-Graph Memory in a Partially Observable Environmentcited by 5
2022GriddlyJS: A Web IDE for Reinforcement Learningcited by 4
2025Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policiescited by 4
2025Rule-Guided Reinforcement Learning Policy Evaluation and Improvementcited by 4
2021DAIR: Disentangled Attention Intrinsic Regularization for Safe and Efficient Bimanual Manipulationcited by 3
2021A Graph Attention Learning Approach to Antenna Tilt Optimizationcited by 3
2024Graph Neural Network Based Action Ranking for Planningcited by 3
2025The Yokai Learning Environment: Tracking Beliefs Over Space and Timecited by 3
2021Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learningcited by 2

50 most cited of 72 All 72 (JSON)