# Predictive Coding for Locally-Linear Control

arXiv: https://arxiv.org/abs/2003.01086 · HTML: https://mlsanity.com/paper/2003.01086/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2020.

## Built on by (most cited first, 17 of 17)

- [Contrastive Learning as Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2206.07568/) (2022)
- [Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models](https://mlsanity.com/paper/2502.14819/) (2025)
- [Temporal Predictive Coding For Model-Based Planning In Latent Space](https://mlsanity.com/paper/2106.07156/) (2021)
- [Temporal Straightening for Latent Planning](https://mlsanity.com/paper/2603.12231/) (2026)
- [Action-Sufficient State Representation Learning for Control with Structural Constraints](https://mlsanity.com/paper/2110.05721/) (2021)
- [Which Mutual-Information Representation Learning Objectives are Sufficient for Control?](https://mlsanity.com/paper/2106.07278/) (2021)
- [INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL](https://mlsanity.com/paper/2204.08585/) (2022)
- [Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference](https://mlsanity.com/paper/2403.04082/) (2024)
- [A Mixture-of-Expert Approach to RL-based Dialogue Management](https://mlsanity.com/paper/2206.00059/) (2022)
- [R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation](https://mlsanity.com/paper/2603.18202/) (2026)
- [Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL](https://mlsanity.com/paper/2302.05342/) (2023)
- [Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks](https://mlsanity.com/paper/2408.05496/) (2024)
- [Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive Architectures](https://mlsanity.com/paper/2508.10489/) (2025)
- [Multi-Step Prediction in Linearized Latent State Spaces for Representation Learning](https://mlsanity.com/paper/2209.01127/) (2022)
- [Learn Proportional Derivative Controllable Latent Space from Pixels](https://mlsanity.com/paper/2110.08239/) (2021)
- [Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization](https://mlsanity.com/paper/2211.06236/) (2022)
- [Learning Macroscopic Dynamics without Reconstructing Microscopic States](https://mlsanity.com/paper/2609.37392/) (2026)

## Abstract (arXiv)

High-dimensional observations and unknown dynamics are major challenges when applying optimal control to many real-world decision making tasks. The Learning Controllable Embedding (LCE) framework addresses these challenges by embedding the observations into a lower dimensional latent space, estimating the latent dynamics, and then performing control directly in the latent space. To ensure the learned latent dynamics are predictive of next-observations, all existing LCE approaches decode back into the observation space and explicitly perform next-observation prediction---a challenging high-dimensional task that furthermore introduces a large number of nuisance parameters (i.e., the decoder) which are discarded during control. In this paper, we propose a novel information-theoretic LCE approach and show theoretically that explicit next-observation prediction can be replaced with predictive coding. We then use predictive coding to develop a decoder-free LCE model whose latent dynamics are amenable to locally-linear control. Extensive experiments on benchmark tasks show that our model reliably learns a controllable latent space that leads to superior performance when compared with state-of-the-art LCE baselines.