Abstract
Several authors have proposed that mechanisms of adaptive behavior, and reinforcement learning in particular, can be explained by an innate tendency of individuals to seek information about the local environment. In this article, I argue that these approaches adhere to an essentialist view of learning that avoids the question why information seeking should be favorable in the first place. I propose a selectionist account of adaptive behavior that explains why individuals behave as if they had a tendency to seek information without resorting to essentialist explanations. I develop my argument using a formal selectionist framework for adaptive behavior, the multilevel model of behavioral selection (MLBS). The MLBS has been introduced recently as a formal theory of behavioral selection that links reinforcement learning to natural selection within a single unified model. I show that the MLBS implies an average gain in information about the availability of reinforcement. Formally, this means that behavior reaches an equilibrium state, if and only if the Fisher information of the conditional probability of reinforcement is maximized. This coincides with a reduction in the randomness of the expected environmental feedback as captured by the information theoretic concept of expected surprise (i.e., entropy). The main result is that behavioral selection maximizes the information about the expected fitness consequences of behavior, which, in turn, minimizes average surprise. In contrast to existing attempts to link adaptive behavior to information theoretic concepts (e.g., the free energy principle), neither information gain nor surprise minimization is treated as a first principle. Instead, the result is formally deduced from the MLBS and therefore constitutes a mathematical property of the more general principle of behavioral selection. Thus, if reinforcement learning is understood as a selection process, there is no need to assume an active agent with an innate tendency to seek information or minimize surprise. Instead, information gain and surprise minimization emerge naturally because it lies in the very nature of selection to produce order from randomness.
Highlights
Many species adapt their behavior to changing environments by mechanisms of learning
In the free energy formulation of predictive coding, adaptive behavior and learning are explained by a tendency to minimize predictive error—a property that is assumed to be constitutive of all living organisms (Friston et al, 2006)
It was shown that the covariance based law of effect can be formally linked to an agent based approach to reinforcement, where the individual adapts its behavior to the environment by predicting the expected consequences of its own behavior
Summary
Reviewed by: Johanni Brea, École Polytechnique Fédérale de Lausanne, Switzerland. A Selectionist Perspective. I show that the MLBS implies an average gain in information about the availability of reinforcement This means that behavior reaches an equilibrium state, if and only if the Fisher information of the conditional probability of reinforcement is maximized. This coincides with a reduction in the randomness of the expected environmental feedback as captured by the information theoretic concept of expected surprise (i.e., entropy). If reinforcement learning is understood as a selection process, there is no need to assume an active agent with an innate tendency to seek information or minimize surprise.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have