A boundedness theoretical analysis for GrADP design: A case study on maze navigation

A new theoretical analysis towards the goal representation adaptive dynamic programming (GrADP) design proposed in [1], [2] is investigated in this paper. Unlike the proofs of convergence for adaptive dynamic programming (ADP) in literature, here we provide a new insight for the error bound between the estimated value function and the expected value function. Then we employ the critic network in GrADP approach to approximate the Q value function, and use the action network to provide the control policy. The goal network is adopted to provide the internal reinforcement signal for the critic network over time. Finally, we illustrate that the estimated Q value function is close to the expected value function in an arbitrary small bound on the maze navigation example.