Abstract:
This paper seeks to establish a mechanism for directing a collection of simple, specialized, self-interested agents to solve what traditionally are posed as monolithic single-agent sequential decision problems with a central global objective. What makes it challenging to use a decentralized approach to collectively optimize a central objective is the difficulty in characterizing the equilibrium strategy profile of non-cooperative games. To overcome this challenge, we design a mechanism for defining the learning environment of each primitive agent for which we know that the optimal solution for the global objective coincides with a Nash equilibrium strategy profile of the agents optimizing their own local objectives. We then derive a learning algorithm for the system and empirically test to what extent the desired equilibrium is achieved. The system functions as an economy of agents that learn the credit assignment process itself by buying and selling to each other the right to operate on the environment state. We also show that redundancy not only enforces credit conservation but also improves robustness against suboptimal equilibria.
