mlsanityData to 14 Oct 2026

Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity

arXiv 2411.01342 ↗First posted 2 Nov 2024cs.LG cs.AIcited by 0

On the map: World models → World models for navigation

Abstract (arXiv)

Developing foundational world models is a key research direction for embodied intelligence, with the ability to adapt to non-stationary environments being a crucial criterion. In this work, we introduce a new formalism, Hidden Parameter-POMDP, designed for control with adaptive world models. We demonstrate that this approach enables learning robust behaviors across a variety of non-stationary RL benchmarks. Additionally, this formalism effectively learns task abstractions in an unsupervised manner, resulting in structured, task-aware latent spaces.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for navigation, one of 11 directions in World models. Builds on 22 of its 28 references that are in the map. First posted on arXiv 2 Nov 2024.

Builds on

22 of 28 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024The Essential Role of Causality in Foundation World Models for Embodied AI6 Feb

Other references · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  4. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  5. 2020Mastering Atari with Discrete World Modelscited by 1,007
  6. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
  7. 2022Temporal Difference Learning for Model Predictive Controlcited by 397
  8. 2020dm_control: Software and Tasks for Continuous Controlcited by 375
  9. 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 274
  10. 2015Deep Kalman Filterscited by 166
  11. 2020An empirical investigation of the challenges of real-world reinforcement learningcited by 77
  12. 2013Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizationscited by 70
9 more
  1. 2019Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spacescited by 67
  2. 2022Contextualize Me -- The Case for Context in Reinforcement Learningcited by 46
  3. 2020Deep Reinforcement Learning amidst Lifelong Non-Stationaritycited by 43
  4. 2024Mastering Memory Tasks with World Modelscited by 38
  5. 2020Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learningcited by 13
  6. 2022On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learningcited by 13
  7. 2022Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarioscited by 8
  8. 2023Multi Time Scale World Modelscited by 8
  9. 2024Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic Perspectivecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling
  2. 2026Benchmarking World Models for Continual Learning on Compositional Tasks
  3. 2026Learning Counterfactual World Models for Embodied Reasoning under Partial Observability
  4. 2025A Survey: Learning Embodied Intelligence from Physical Simulators and World Models
  5. 2025World-in-World: World Models in a Closed-Loop World
  6. 2026Sensorimotor World Models: Perception for Action via Inverse Dynamics
  7. 2026LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations
  8. 2026Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling