# Emergence of Goal-Directed Behaviors via Active Inference with Self-Prior

arXiv: https://arxiv.org/abs/2504.11075 · HTML: https://mlsanity.com/paper/2504.11075/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 58 references that are in the map.
- First posted on arXiv 15 Apr 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Neural Spline Flows](https://mlsanity.com/paper/1906.04032/) (2019)
- [TransDreamer: Reinforcement Learning with Transformer World Models](https://mlsanity.com/paper/2202.09481/) (2022)
- [Deep Active Inference as Variational Policy Gradients](https://mlsanity.com/paper/1907.03876/) (2019)
- [On the Relationship Between Active Inference and Control as Inference](https://mlsanity.com/paper/2006.12964/) (2020)
- [An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey](https://mlsanity.com/paper/2209.08890/) (2022)
- [End-to-End Pixel-Based Deep Active Inference for Body Perception and Action](https://mlsanity.com/paper/2001.05847/) (2019)
- [Contrastive Active Inference](https://mlsanity.com/paper/2110.10083/) (2021)
- [Exploration and preference satisfaction trade-off in reward-free learning](https://mlsanity.com/paper/2106.04316/) (2021)
- [Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop](https://mlsanity.com/paper/1806.08083/) (2018)
- [Goal-directed Planning and Goal Understanding by Active Inference: Evaluation Through Simulated and Physical Robot Experiments](https://mlsanity.com/paper/2202.09976/) (2022)
- [Body models in humans, animals, and robots: mechanisms and plasticity](https://mlsanity.com/paper/2010.09325/) (2020)

## Built on by (most cited first, 1 of 1)

- [Active Inference with a Self-Prior in the Mirror-Mark Task](https://mlsanity.com/paper/2604.09673/) (2026)

## Abstract (arXiv)

Infants often exhibit goal-directed behaviors, such as reaching for a sensory stimulus, even when no external reward criterion is provided. These intrinsically motivated behaviors facilitate spontaneous exploration and learning of the body and environment during early developmental stages. Although computational modeling can offer insight into the mechanisms underlying such behaviors, many existing studies on intrinsic motivation focus primarily on how exploration contributes to acquiring external rewards. In this paper, we propose a novel density model for an agent's own multimodal sensory experiences, called the "self-prior," and investigate whether it can autonomously induce goal-directed behavior. Integrated within an active inference framework based on the free energy principle, the self-prior generates behavioral references purely from an intrinsic process that minimizes mismatches between average past sensory experiences and current observations. This mechanism is also analogous to the acquisition and utilization of a body schema through continuous interaction with the environment. We examine this approach in a simulated environment and confirm that the agent spontaneously reaches toward a tactile stimulus. Our study implements intrinsically motivated behavior shaped by the agent's own sensory experiences, demonstrating the spontaneous emergence of intentional behavior during early development.