# Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning

arXiv: https://arxiv.org/abs/2010.10201 · HTML: https://mlsanity.com/paper/2010.10201/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2020.

## Built on by (most cited first, 13 of 13)

- [On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2210.09256/) (2022)
- [Efficient Dynamics Modeling in Interactive Environments with Koopman Theory](https://mlsanity.com/paper/2306.11941/) (2023)
- [KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty](https://mlsanity.com/paper/2406.15131/) (2024)
- [Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios](https://mlsanity.com/paper/2206.14697/) (2022)
- [Multi Time Scale World Models](https://mlsanity.com/paper/2310.18534/) (2023)
- [Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modelling and State Tracking](https://mlsanity.com/paper/2602.10743/) (2026)
- [Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/2409.16824/) (2024)
- [End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control](https://mlsanity.com/paper/2205.13804/) (2022)
- [Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive Architectures](https://mlsanity.com/paper/2508.10489/) (2025)
- [Context-Conditional Navigation with a Learning-Based Terrain- and Robot-Aware Dynamics Model](https://mlsanity.com/paper/2307.09206/) (2023)
- [Learning a Terrain- and Robot-Aware Dynamics Model for Autonomous Mobile Robot Navigation](https://mlsanity.com/paper/2409.11452/) (2024)
- [Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity](https://mlsanity.com/paper/2411.01342/) (2024)
- [Model-Free Neural Filtering: A Comparison with Classical Filters in Nonlinear Systems](https://mlsanity.com/paper/2601.21266/) (2026)

## Abstract (arXiv)

Estimating accurate forward and inverse dynamics models is a crucial component of model-based control for sophisticated robots such as robots driven by hydraulics, artificial muscles, or robots dealing with different contact situations. Analytic models to such processes are often unavailable or inaccurate due to complex hysteresis effects, unmodelled friction and stiction phenomena,and unknown effects during contact situations. A promising approach is to obtain spatio-temporal models in a data-driven way using recurrent neural networks, as they can overcome those issues. However, such models often do not meet accuracy demands sufficiently, degenerate in performance for the required high sampling frequencies and cannot provide uncertainty estimates. We adopt a recent probabilistic recurrent neural network architecture, called Re-current Kalman Networks (RKNs), to model learning by conditioning its transition dynamics on the control actions. RKNs outperform standard recurrent networks such as LSTMs on many state estimation tasks. Inspired by Kalman filters, the RKN provides an elegant way to achieve action conditioning within its recurrent cell by leveraging additive interactions between the current latent state and the action variables. We present two architectures, one for forward model learning and one for inverse model learning. Both architectures significantly outperform exist-ing model learning frameworks as well as analytical models in terms of prediction performance on a variety of real robot dynamics models.