On Predictive planning and counterfactual learning in active inference
This work addresses decision-making in AI agents, but appears incremental as it builds on existing active inference theory with a hybrid approach.
The paper tackles the challenge of balancing planning and learning in decision-making by introducing a mixed model that navigates the data-complexity trade-off between these strategies, evaluated in a grid-world scenario requiring adaptability.
Given the rapid advancement of artificial intelligence, understanding the foundations of intelligent behaviour is increasingly important. Active inference, regarded as a general theory of behaviour, offers a principled approach to probing the basis of sophistication in planning and decision-making. In this paper, we examine two decision-making schemes in active inference based on 'planning' and 'learning from experience'. Furthermore, we also introduce a mixed model that navigates the data-complexity trade-off between these strategies, leveraging the strengths of both to facilitate balanced decision-making. We evaluate our proposed model in a challenging grid-world scenario that requires adaptability from the agent. Additionally, our model provides the opportunity to analyze the evolution of various parameters, offering valuable insights and contributing to an explainable framework for intelligent decision-making.