English

Deep Active Inference for Pixel-Based Discrete Control: Evaluation on the Car Racing Problem

Artificial Intelligence 2021-09-10 v1 Neural and Evolutionary Computing

Abstract

Despite the potential of active inference for visual-based control, learning the model and the preferences (priors) while interacting with the environment is challenging. Here, we study the performance of a deep active inference (dAIF) agent on OpenAI's car racing benchmark, where there is no access to the car's state. The agent learns to encode the world's state from high-dimensional input through unsupervised representation learning. State inference and control are learned end-to-end by optimizing the expected free energy. Results show that our model achieves comparable performance to deep Q-learning. However, vanilla dAIF does not reach state-of-the-art performance compared to other world model approaches. Hence, we discuss the current model implementation's limitations and potential architectures to overcome them.

Keywords

Cite

@article{arxiv.2109.04155,
  title  = {Deep Active Inference for Pixel-Based Discrete Control: Evaluation on the Car Racing Problem},
  author = {Niels van Hoeffelen and Pablo Lanillos},
  journal= {arXiv preprint arXiv:2109.04155},
  year   = {2021}
}

Comments

2nd International Workshop on Active Inference IWAI2021, European Conference on Machine Learning (ECML/PCKDD 2021)

R2 v1 2026-06-24T05:49:09.558Z