A Brandom-ian view of Reinforcement Learning towards strong-AI

TL;DR

This paper integrates Brandom's inferentialist philosophy with reinforcement learning, proposing a restructured A3C algorithm aimed at advancing towards strong artificial intelligence.

Contribution

It introduces a novel theoretical framework connecting Brandom's philosophy with RL, and modifies A3C to align with strong-AI development goals.

Findings

Reformulated A3C based on Brandom's ideas

Theoretical link between inferentialism and RL

Potential pathway to strong-AI through philosophical integration

Abstract

The analytic philosophy of Robert Brandom, based on the ideas of pragmatism, paints a picture of sapience, through inferentialism. In this paper, we present a theory, that utilizes essential elements of Brandom's philosophy, towards the objective of achieving strong-AI. We do this by connecting the constitutive elements of reinforcement learning and the Game Of Giving and Asking For Reasons. Further, following Brandom's prescriptive thoughts, we restructure the popular reinforcement learning algorithm A3C, and show that RL algorithms can be tuned towards the objective of strong-AI.