{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-active-inference-for-pixel-based","title":"Deep Active Inference for Pixel-Based Discrete Control: Evaluation on the Car Racing Problem","arxiv_id":"2109.04155","date":"2021-09-09","proceeding":null,"authors":["Niels van Hoeffelen","Pablo Lanillos"],"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.","url_abs":"https://arxiv.org/abs/2109.04155v1","url_pdf":"https://arxiv.org/pdf/2109.04155v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-active-inference-for-pixel-based","repo_url":"https://github.com/ntavanhoeffelen/daif_carracing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"car-racing","task_name":"Car Racing"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}