The Free Energy Principle for Perception and Action: A Deep Learning Perspective

Abstract

The free energy principle, and its corollary active inference, constitute a bio-inspired theory that assumes biological agents act to remain in a restricted set of preferred states of the world, i.e., they minimize their free energy. Under this principle, biological agents learn a generative model of the world and plan actions in the future that will maintain the agent in an homeostatic state that satisfies its preferences. This framework lends itself to being realized in silico, as it comprehends important aspects that make it computationally affordable, such as variational inference and amortized planning. In this work, we investigate the tool of deep learning to design and realize artificial agents based on active inference, presenting a deep-learning oriented presentation of the free energy principle, surveying works that are relevant in both machine learning and active inference areas, and discussing the design choices that are involved in the implementation process. This manuscript probes newer perspectives for the active inference framework, grounding its theoretical aspects into more pragmatic affairs, offering a practical guide to active inference newcomers and a starting point for deep learning practitioners that would like to investigate implementations of the free energy principle.

References in corpus (15)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Bootstrap your own latent: A new approach to self-supervised Learning
• Weight Uncertainty in Neural Networks
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Alias-Free Generative Adversarial Networks
• Solving Rubik's Cube with a Robot Hand
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Active inference, eye movements and oculomotor delays
• Planning to Explore via Self-Supervised World Models
• Reinforcement Learning through Active Inference
• Active Inference in Robotics and Artificial Agents: Survey and Challenges
• Model-Augmented Actor-Critic: Backpropagating through Paths
• Bayesian policy selection using active inference
• Clockwork Variational Autoencoders
• Exploration and preference satisfaction trade-off in reward-free learning

Cited by in corpus (1)

• Symmetry and Complexity in Object-Centric Deep Active Inference Models