mlsanityData to 14 Oct 2026

On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective

arXiv 2212.12669 ↗First posted 24 Dec 2022cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

The pervasive uncertainty and dynamic nature of real-world environments present significant challenges for the widespread implementation of machine-driven Intelligent Decision-Making (IDM) systems. Consequently, IDM should possess the ability to continuously acquire new skills and effectively generalize across a broad range of applications. The advancement of Artificial General Intelligence (AGI) that transcends task and application boundaries is critical for enhancing IDM. Recent studies have extensively investigated the Transformer neural architecture as a foundational model for various tasks, including computer vision, natural language processing, and reinforcement learning. We propose that a Foundation Decision Model (FDM) can be developed by formulating diverse decision-making tasks as sequence decoding tasks using the Transformer architecture, offering a promising solution for expanding IDM applications in complex real-world situations. In this paper, we discuss the efficiency and generalization improvements offered by a foundation decision model for IDM and explore its potential applications in multi-agent game AI, production scheduling, and robotics tasks. Lastly, we present a case study demonstrating our FDM implementation, DigitalBrain (DB1) with 1.3 billion parameters, achieving human-level performance in 870 tasks, such as text generation, image captioning, video game playing, robotic control, and traveling salesman problems. As a foundation decision model, DB1 represents an initial step toward more autonomous and efficient real-world IDM applications.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 49 of its 105 references that are in the map. First posted on arXiv 24 Dec 2022.

Builds on

49 of 105 references.

References · 49

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  6. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  7. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  8. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  9. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  10. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  11. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  12. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
37 more
  1. 2020GLU Variants Improve Transformercited by 1,804
  2. 2016Generative Adversarial Imitation Learningcited by 1,597
  3. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  4. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,462
  5. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  6. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  7. 2020On Layer Normalization in the Transformer Architecturecited by 922
  8. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
  9. 2017A Survey on Multi-Task Learningcited by 840
  10. 2022A Generalist Agentcited by 808
  11. 2019Multimodal Transformer for Unaligned Multimodal Language Sequencescited by 645
  12. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 644
  13. 2022Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Taskscited by 511
  14. 2022Transformers in Time Series: A Surveycited by 497
  15. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  16. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 478
  17. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 465
  18. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
  19. 2022Multimodal Learning with Transformers: A Surveycited by 400
  20. 2020dm_control: Software and Tasks for Continuous Controlcited by 375
  21. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 345
  22. 2017A Structured Self-attentive Sentence Embeddingcited by 318
  23. 2020Agent57: Outperforming the Atari Human Benchmarkcited by 303
  24. 2018BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learningcited by 244
  25. 2018Distributed Distributional Deterministic Policy Gradientscited by 199
  26. 2021Trust Region Policy Optimisation in Multi-Agent Reinforcement Learningcited by 186
  27. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  28. 2022Multi-Agent Reinforcement Learning is a Sequence Modeling Problemcited by 155
  29. 2017Imagination-Augmented Agents for Deep Reinforcement Learningcited by 140
  30. 2020One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Controlcited by 121
  31. 2019Look, Listen, and Act: Towards Audio-Visual Embodied Navigationcited by 96
  32. 2020Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learningcited by 93
  33. 2017One Model To Learn Them Allcited by 87
  34. 2021NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learningcited by 63
  35. 2016Display Advertising with Real-Time Bidding (RTB) and Behavioural Targetingcited by 42
  36. 2019Off-Policy Actor-Critic with Shared Experience Replaycited by 39
  37. 2018One Big Net For Everythingcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 2; 2026: 1.

8 papers.

  1. 2023Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learningcited by 115
  2. 2024Reinforcing Language Agents via Policy Optimization with Action Decompositioncited by 16
  3. 2023GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Modelscited by 5
  4. 2025Trajectory World Models for Heterogeneous Environmentscited by 4
  5. 2024Fourier Controller Networks for Real-Time Decision-Making in Embodied Learningcited by 3
  6. 2024Building Decision Making Models Through Language Model Regimecited by 2
  7. 2025UniCO: Towards a Unified Model for Combinatorial Optimization Problemscited by 2
  8. 2026WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systemscited by 1