Related papers: Intrinsic motivation as constrained entropy maximi…
To be capable of lifelong learning in a real-life environment, robots have to tackle multiple challenges. Being able to relate physical properties they may observe in their environment to possible interactions they may have is one of them.…
The reinforcement learning (RL) research area is very active, with an important number of new contributions; especially considering the emergent field of deep RL (DRL). However a number of scientific and technical challenges still need to…
Attractor dynamics are a hallmark of many complex systems, including the brain. Understanding how such self-organizing dynamics emerge from first principles is crucial for advancing our understanding of neuronal computations and the design…
What is the nature of curiosity? Is there any scientific way to understand the origin of this mysterious force that drives the behavior of even the stupidest naturally intelligent systems and is completely absent in their smartest…
Intrinsic rewards were introduced to simulate how human intelligence works; they are usually evaluated by intrinsically-motivated play, i.e., playing games without extrinsic rewards but evaluated with extrinsic rewards. However, none of the…
Exploration in complex domains is a key challenge in reinforcement learning, especially for tasks with very sparse rewards. Recent successes in deep reinforcement learning have been achieved mostly using simple heuristic exploration…
We model endogenous perception of private information in single-agent screening problems, with potential evaluation errors. The agent's evaluation of their type depends on their cognitive state: either attentive (i.e., they correctly…
Exploring rich environments and evaluating one's actions without prior knowledge is immensely challenging. In this paper, we propose Motif, a general method to interface such prior knowledge from a Large Language Model (LLM) with an agent.…
Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…
The concept of free energy has its origins in 19th century thermodynamics, but has recently found its way into the behavioral and neural sciences, where it has been promoted for its wide applicability and has even been suggested as a…
We pose an active perception problem where an autonomous agent actively interacts with a second agent with potentially adversarial behaviors. Given the uncertainty in the intent of the other agent, the objective is to collect further…
Transparency and explainability are important features that responsible autonomous vehicles should possess, particularly when interacting with humans, and causal reasoning offers a strong basis to provide these qualities. However, even if…
Active inference is a normative framework for explaining behaviour under the free energy principle -- a theory of self-organisation originating in neuroscience. It specifies neuronal dynamics for state-estimation in terms of a descent on…
Active systems across scales, ranging from molecular machines to human crowds, are usually modeled as assemblies of self-propelled particles driven by internally generated forces. However, these models often assume memoryless dynamics and…
This chapter revisits the concept of excitability, a basic system property of neurons. The focus is on excitable systems regarded as behaviors rather than dynamical systems. By this we mean open systems modulated by specific interconnection…
Sparsity of rewards while applying a deep reinforcement learning method negatively affects its sample-efficiency. A viable solution to deal with the sparsity of rewards is to learn via intrinsic motivation which advocates for adding an…
Intentions are crucial for our practical reasoning. The rational intention obeys some simple logical principles, such as agglomeration and consistency, among others, motivating the search for a proper logic of intention. However, such a…
Maximum Entropy is a powerful concept that entails a sharp separation between relevant and irrelevant variables. It is typically invoked in inference, once an assumption is made on what the relevant variables are, in order to estimate a…
The excess work required to drive a stochastic system out of thermodynamic equilibrium through a time-dependent external perturbation is directly related to the amount of entropy produced during the driving process, allowing excess work and…
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…