Adaptive critic methods have common roots as generalizations of dynamic programming for neural reinforcement learning approaches. Since they approximate the dynamic programming solutions, they are potentially suitable for learning in noisy, nonlinear and nonstationary environments. In this study, a novel probabilistic dual heuristic programming (DHP) based adaptive critic controller is proposed...

Neural networks and reinforcement learning have successfully been applied to various games, such as Ms. Pacman and Go. We combine multilayer perceptrons and a class of reinforcement learning algorithms known as actor-critic to learn to play the arcade classic Donkey Kong. Two neural networks are used in this study: the actor and the critic. The actor learns to select the best action given the g...

Abstract (1) Suppose that you care only about speaking the truth, and are confident some particular deterministic theory is true. If someone asks whether true, rationally required to answer ‘yes’? (2) face a problem in which (as Newcomb's problem) one of your options – call it ‘taking two boxes’ causally dominates other option. Are take boxes? Those us attracted causal decision under pressure ‘...

Abstract Scholars of political thought often view Plato as a ‘political moralist’, or ‘utopian’ partly due to the Republic’s emphasis on ‘justice’. But in Republic, offers distinctive theory legitimacy, one that grounds legitimacy an interdependent relationship between justice and moderation. Justice requires principle specialisation be respected, while moderation citizens agree about who shoul...

We present an analysis of actor/critic algorithms, in which the actor updates its policy using eligibility traces of the policy parameters. Most of the theoretical results for eligibility traces have been for only critic's value iteration algorithms. This paper investigates what the actor's eligibility trace does. The results show that the algorithm is an extension of Williams' REINFORCE algori...