mlsanityData to 14 Oct 2026

Temporal Difference Variational Auto-Encoder

arXiv 1806.03107 ↗First posted 8 Jun 2018cs.LG stat.MLcited by 49

Not on the map. Why?

Abstract (arXiv)

To act and plan in complex environments, we posit that agents should have a mental simulator of the world with three characteristics: (a) it should build an abstract state representing the condition of the world; (b) it should form a belief which represents uncertainty on the world; (c) it should go beyond simple step-by-step simulation, and exhibit temporal abstraction. Motivated by the absence of a model satisfying all these requirements, we propose TD-VAE, a generative sequence model that learns representations containing explicit beliefs about states several steps into the future, and that can be rolled out directly without single-step transitions. TD-VAE is trained on pairs of temporally separated time points, using an analogue of temporal difference learning used in reinforcement learning.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 13; 2022: 12; 2023: 7; 2024: 9; 2025: 4; 2026: 3.

49 papers.

Sort:

By area:

  1. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigationcited by 85
  2. 2022StretchBEV: Stretching Future Instance Prediction Spatially and Temporallycited by 47
  3. 2022Retrospectives on the Embodied AI Workshopcited by 46
  4. 2021Clockwork Variational Autoencoderscited by 42
  5. 2021SLAMP: Stochastic Latent Appearance and Motion Predictioncited by 32
  6. 2021Action-Sufficient State Representation Learning for Control with Structural Constraintscited by 31
  7. 2019Learning Belief Representations for Imitation Learning in POMDPscited by 24
  8. 2021Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Surveycited by 24
  9. 2021Online Variational Filtering and Parameter Learningcited by 19
  10. 2022Abstraction for Deep Reinforcement Learningcited by 19
  11. 2021Neural Recursive Belief States in Multi-Agent Reinforcement Learningcited by 18
  12. 2022Flow-based Recurrent Belief State Learning for POMDPscited by 16
37 more
  1. 2021Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Modelscited by 14
  2. 2022Unsupervised Learning of Temporal Abstractions with Slot-based Transformerscited by 14
  3. 2023Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysiscited by 13
  4. 2024EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Datacited by 13
  5. 2021Training a Resilient Q-Network against Observational Interferencecited by 9
  6. 2021Variational Predictive Routing with Nested Subjective Timescalescited by 9
  7. 2023The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Modelscited by 9
  8. 2023Strata-NeRF : Neural Radiance Fields for Stratified Scenescited by 7
  9. 2021VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Expertscited by 6
  10. 2022Competency Assessment for Autonomous Agents using Deep Generative Modelscited by 6
  11. 2024Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videoscited by 6
  12. 2021A Temporal Variational Model for Story Generationcited by 5
  13. 2024Learning Abstract World Model for Value-preserving Planning with Optionscited by 4
  14. 2024Representation Learning For Efficient Deep Multi-Agent Reinforcement Learningcited by 3
  15. 2025Versatile Physics-based Character Control with Hybrid Latent Representationcited by 3
  16. 2021Piecewise-constant Neural ODEscited by 2
  17. 2022Q-learning with online random forestscited by 2
  18. 2022DIDER: Discovering Interpretable Dynamically Evolving Relationscited by 2
  19. 2024Grouped Discrete Representation Guides Object-Centric Learningcited by 2
  20. 2024Towards Cost Sensitive Decision Makingcited by 2
  21. 2022Wildfire Forecasting with Satellite Images and Deep Generative Modelcited by 1
  22. 2023Policy Evaluation in Decentralized POMDPs with Belief Sharingcited by 1
  23. 2023Personalization Disentanglement for Federated Learning: An explainable perspectivecited by 1
  24. 2023A Metalearned Neural Circuit for Nonparametric Bayesian Inferencecited by 1
  25. 2025Unraveling Hidden Representations: A Multi-Modal Layer Analysis for Better Synthetic Content Forensicscited by 1
  26. 2026Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Makingcited by 1
  27. 2021Pixyz: a Python library for developing deep generative modelscited by 0
  28. 2022Dual reparametrized Variational Generative Model for Time-Series Forecastingcited by 0
  29. 2022Hub-VAE: Unsupervised Hub-based Regularization of Variational Autoencoderscited by 0
  30. 2022Decentralized cooperative perception for autonomous vehicles: Learning to value the unknowncited by 0
  31. 2024Sequential Model for Predicting Patient Adherence in Subcutaneous Immunotherapy for Allergic Rhinitiscited by 0
  32. 2024State-space Decomposition Model for Video Prediction Considering Long-term Motion Trendcited by 0
  33. 2024Reinforcement Learning of Adaptive Acquisition Policies for Inverse Problemscited by 0
  34. 2025EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learningcited by 0
  35. 2025Imagine Beyond! Distributionally Robust Auto-Encoding for State Space Coverage in Online Reinforcement Learningcited by 0
  36. 2026Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillationcited by 0
  37. 2026Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamicscited by 0