# Deep hybrid models: infer and plan in a dynamic world

arXiv: https://arxiv.org/abs/2402.10088 · HTML: https://mlsanity.com/paper/2402.10088/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 94 references that are in the map.
- First posted on arXiv 1 Feb 2024.

## Builds on (most cited first, 28 of 28)

- [Active inference on discrete state-spaces: a synthesis](https://mlsanity.com/paper/2001.07203/) (2020)
- [Predictive Coding Approximates Backprop along Arbitrary Computation Graphs](https://mlsanity.com/paper/2006.04182/) (2020)
- [Deep active inference agents using Monte-Carlo methods](https://mlsanity.com/paper/2006.04176/) (2020)
- [Sophisticated Inference](https://mlsanity.com/paper/2006.04120/) (2020)
- [Temporal Predictive Coding For Model-Based Planning In Latent Space](https://mlsanity.com/paper/2106.07156/) (2021)
- [Deep Active Inference as Variational Policy Gradients](https://mlsanity.com/paper/1907.03876/) (2019)
- [Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?](https://mlsanity.com/paper/2202.09467/) (2022)
- [Deep Active Inference](https://mlsanity.com/paper/1709.02341/) (2017)
- [The Neural Coding Framework for Learning Generative Models](https://mlsanity.com/paper/2012.03405/) (2020)
- [On the Relationship Between Active Inference and Control as Inference](https://mlsanity.com/paper/2006.12964/) (2020)
- [Model-based Reinforcement Learning: A Survey](https://mlsanity.com/paper/2006.16712/) (2020)
- [Brain-inspired Computational Intelligence via Predictive Coding](https://mlsanity.com/paper/2308.07870/) (2023)
- [The free energy principle made simpler but not too simple](https://mlsanity.com/paper/2201.06387/) (2022)
- [End-to-End Pixel-Based Deep Active Inference for Body Perception and Action](https://mlsanity.com/paper/2001.05847/) (2019)
- [Bayesian model reduction](https://mlsanity.com/paper/1805.07092/) (2018)
- [Sequential Memory with Temporal Predictive Coding](https://mlsanity.com/paper/2305.11982/) (2023)
- [Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks](https://mlsanity.com/paper/2103.03725/) (2021)
- [Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning](https://mlsanity.com/paper/2210.13461/) (2022)
- [Hierarchical generative modelling for autonomous robots](https://mlsanity.com/paper/2308.07775/) (2023)
- [A deep active inference model of the rubber-hand illusion](https://mlsanity.com/paper/2008.07408/) (2020)
- [Object-based active inference](https://mlsanity.com/paper/2209.01258/) (2022)
- [Disentangling Shape and Pose for Object-Centric Deep Active Inference Models](https://mlsanity.com/paper/2209.09097/) (2022)
- [Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems](https://mlsanity.com/paper/2209.09174/) (2022)
- [Designing explainable artificial intelligence with active inference: A framework for transparent introspection and decision-making](https://mlsanity.com/paper/2306.04025/) (2023)
- [Deconstructing deep active inference](https://mlsanity.com/paper/2303.01618/) (2023)
- [Recursive Neural Programs: Variational Learning of Image Grammars and Part-Whole Hierarchies](https://mlsanity.com/paper/2206.08462/) (2022)
- [Object-Centric Scene Representations using Active Inference](https://mlsanity.com/paper/2302.03288/) (2023)
- [Modeling motor control in continuous-time Active Inference: a survey](https://mlsanity.com/paper/2310.05144/) (2023)

## Abstract (arXiv)

To determine an optimal plan for complex tasks, one often deals with dynamic and hierarchical relationships between several entities. Traditionally, such problems are tackled with optimal control, which relies on the optimization of cost functions; instead, a recent biologically-motivated proposal casts planning and control as an inference process. Active inference assumes that action and perception are two complementary aspects of life whereby the role of the former is to fulfill the predictions inferred by the latter. Here, we present an active inference approach that exploits discrete and continuous processing, based on three features: the representation of potential body configurations in relation to the objects of interest; the use of hierarchical relationships that enable the agent to easily interpret and flexibly expand its body schema for tool use; the definition of potential trajectories related to the agent's intentions, used to infer and plan with dynamic elements at different temporal scales. We evaluate this deep hybrid model on a habitual task: reaching a moving object after having picked a moving tool. We show that the model can tackle the presented task under different conditions. This study extends past work on planning as inference and advances an alternative direction to optimal control.