mlsanityData to 7 Oct 2026

Context is Everything: Implicit Identification for Dynamics Adaptation

arXiv 2203.05549 ↗First posted 10 Mar 2022cs.RO cs.AI cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

Understanding environment dynamics is necessary for robots to act safely and optimally in the world. In realistic scenarios, dynamics are non-stationary and the causal variables such as environment parameters cannot necessarily be precisely measured or inferred, even during training. We propose Implicit Identification for Dynamics Adaptation (IIDA), a simple method to allow predictive models to adapt to changing environment dynamics. IIDA assumes no access to the true variations in the world and instead implicitly infers properties of the environment from a small amount of contextual data. We demonstrate IIDA's ability to perform well in unseen environments through a suite of simulated experiments on MuJoCo environments and a real robot dynamic sliding task. In general, IIDA significantly reduces model error and results in higher task performance over commonly used methods. Our code and robot videos are at https://bennevans.github.io/iida/

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 10 Mar 2022.

Builds on

30 of 43 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  6. 2016OpenAI Gymcited by 1,684
  7. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  8. 2019Solving Rubik's Cube with a Robot Handcited by 699
  9. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 636
  10. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  11. 2019Meta-Learning with Implicit Gradientscited by 523
  12. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
18 more
  1. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  2. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  3. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 312
  4. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 229
  5. 2017One-Shot Visual Imitation Learning via Meta-Learningcited by 225
  6. 2015Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hourscited by 208
  7. 2018Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experiencecited by 203
  8. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 202
  9. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 138
  10. 2016EPOpt: Learning Robust Neural Network Policies Using Model Ensemblescited by 136
  11. 2017Preparing for the Unknown: Learning a Universal Policy with Online System Identificationcited by 129
  12. 2020Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learningcited by 95
  13. 2021Evolving Reinforcement Learning Algorithmscited by 48
  14. 2019Environment Probing Interaction Policiescited by 39
  15. 2020Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloadscited by 27
  16. 2015One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priorscited by 26
  17. 2020Fast Online Adaptation in Robotics through Meta-Learning Embeddings of Simulated Priorscited by 21
  18. 2018Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical systemcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 6; 2025: 9; 2026: 5.

26 papers.

Sort:

By area:

  1. 2025PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videoscited by 78
  2. 2024AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulationcited by 52
  3. 2024Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modelingcited by 42
  4. 2025Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulationcited by 42
  5. 2023The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objectscited by 40
  6. 2025PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulationcited by 22
  7. 2023AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfercited by 17
  8. 2022Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Controlcited by 13
  9. 2022That Sounds Right: Auditory Self-Supervision for Dynamic Robot Manipulationcited by 12
  10. 2024Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identificationscited by 10
  11. 2025PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesiscited by 9
  12. 2025Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalizationcited by 5
14 more
  1. 2025NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videoscited by 4
  2. 2023Moving Forward by Moving Backward: Embedding Action Impact over Action Semanticscited by 3
  3. 2025LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrationscited by 3
  4. 2024Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learningcited by 2
  5. 2024Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learningcited by 2
  6. 2026Learning Physics-Guided Residual Dynamics for Deformable Object Simulationcited by 2
  7. 2022Open-Ended Diverse Solution Discovery with Regulated Behavior Patterns for Cross-Domain Adaptationcited by 1
  8. 2025Beyond Context: Large Language Models' Failure to Grasp Users' Intentcited by 1
  9. 2026DADP: Domain Adaptive Diffusion Policycited by 1
  10. 2026Contextual Intelligence The Next Leap for Reinforcement Learningcited by 1
  11. 2024One-shot World Models Using a Transformer Trained on a Synthetic Priorcited by 0
  12. 2025AD-NODE: Adaptive Dynamics Learning with Neural ODEs for Mobile Robots Controlcited by 0
  13. 2026MATE: Solving Contextual Markov Decision Processes with Memory of Accumulated Transition Embeddingscited by 0
  14. 2026Dynamic Context Scheduling: Learning Beyond the Static Universecited by 0