A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making
Not on the map. Why?
Abstract (arXiv)
In the field of Sequential Decision Making (SDM), two paradigms have historically vied for supremacy: Automated Planning (AP) and Reinforcement Learning (RL). In the spirit of reconciliation, this article reviews AP, RL and hybrid methods (e.g., novel learn to plan techniques) for solving Sequential Decision Processes (SDPs), focusing on their knowledge representation: symbolic, subsymbolic, or a combination. Additionally, it also covers methods for learning the SDP structure. Finally, we compare the advantages and drawbacks of the existing methods and conclude that neurosymbolic AI poses a promising approach for SDM, since it combines AP and RL with a hybrid knowledge representation.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 53 of its 224 references that are in the map. First posted on arXiv 20 Apr 2023.
Builds on
53 of 224 references.
References · 53
- 2017Attention Is All You Needcited by 60,361
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
- 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
- 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
- 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 509
- 2019Model-Based Reinforcement Learning for Ataricited by 502
- 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 465
- 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 298
- 2021Combinatorial optimization and reasoning with graph neural networkscited by 268
38 more
- 2018Deep Learning: A Critical Appraisalcited by 217
- 2019Contrastive Learning of Structured World Modelscited by 209
- 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 196
- 2016Value Iteration Networkscited by 160
- 2016Continuous Deep Q-Learning with Model-based Accelerationcited by 157
- 2019Neural Logic Machinescited by 145
- 2016A Compositional Object-Based Approach to Learning Physical Dynamicscited by 119
- 2017Value Prediction Networkcited by 117
- 2017A Laplacian Framework for Option Discovery in Reinforcement Learningcited by 110
- 2020The Value Equivalence Principle for Model-Based Reinforcement Learningcited by 94
- 2016The Predictron: End-To-End Learning and Planningcited by 93
- 2014The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarkscited by 87
- 2017Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learningcited by 83
- 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 78
- 2017Recurrent Environment Simulatorscited by 68
- 2019An investigation of model-free planningcited by 66
- 2017Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physicscited by 58
- 2020Reinforcement Learning in Economics and Financecited by 58
- 2018PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Makingcited by 52
- 2019Learning Domain-Independent Planning Heuristics with Hypergraph Networkscited by 50
- 2016Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networkscited by 49
- 2016Learning to Perform Physics Experiments via Deep Reinforcement Learningcited by 47
- 2015From Pixels to Torques: Policy Learning with Deep Dynamical Modelscited by 45
- 2020The Emerging Landscape of Explainable AI Planning and Decision Makingcited by 44
- 2016Towards Deep Symbolic Reinforcement Learningcited by 42
- 2020Model-based Reinforcement Learning: A Surveycited by 39
- 2018Learning to Search with MCTSnetscited by 33
- 2017Action Schema Networks: Generalised Policies with Deep Learningcited by 32
- 2017Learning model-based planning from scratchcited by 22
- 2021Classical Planning in Deep Latent Spacecited by 22
- 2019Landmark-Based Approaches for Goal Recognition as Planningcited by 21
- 2021Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generatorscited by 21
- 2018Curiosity Driven Exploration of Learned Disentangled Goal Spacescited by 16
- 2021High-Accuracy Model-Based Reinforcement Learning, a Surveycited by 13
- 2017TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learningcited by 12
- 2018Towards a Simple Approach to Multi-step Model-based Reinforcement Learningcited by 9
- 2013SPUDD: Stochastic Planning using Decision Diagramscited by 7
- 2017Generative Temporal Models with Memorycited by 6
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2024: 2.
2 papers.