Can I read Deep Active Inference for Pixel-Based Discrete Control: Evaluation on the Car Racing Problem on EtoBox?

Deep Active Inference for Pixel-Based Discrete Control: Evaluation on the Car Racing Problem by van Hoeffelen, Niels; Lanillos, Pablo is a scholarly article available to read on EtoBox.

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

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.

Author

van Hoeffelen, Niels; Lanillos, Pablo

Published

2021

Language

EN