Symbolic interaction and reinforcement theory

Symbolic interaction theory and architecture

Towards Deep Symbolic Reinforcement Learning

Deep reinforcement learning (DRL) brings the power of deep neural networks to bear on the generic task of trial-and-error learning, and its effectiveness has been convincingly demonstrated on tasks such as Atari video games and the game of Go. However, contemporary DRL systems inherit a number of shortcomings from the current generation of deep learning techniques. For example, they require ver...

Combining Reinforcement Learning with Symbolic Planning

One of the major difficulties in applying Q-learning to realworld domains is the sharp increase in the number of learning steps required to converge towards an optimal policy as the size of the state space is increased. In this paper we propose a method, PLANQ-learning, that couples a Q-learner with a STRIPS planner. The planner shapes the reward function, and thus guides the Q-learner quickly ...

Recursion Theory and Symbolic Dynamics

A set P ⊆ {0,1}N may be viewed as a mass problem, i.e., a decision problem with more than one solution. By definition, the solutions of P are the elements of P . A mass problem is said to be solvable if at least one of its solutions is recursive. A mass problem P is said to be Muchnik reducible to a mass problem Q if for each solution of Q there exists a solution of P which is Turing reducible ...

Symbolic Neutrosophic Theory

Symbolic (or Literal) Neutrosophic Theory is referring to the use of abstract symbols (i.e. the letters T, I, F, or their refined indexed letters Tj, Ik, Fl) in neutrosophics. We extend the dialectical triad thesis-antithesis-synthesis to the neutrosophic tetrad thesis-antithesis-neutrothesis-neutrosynthesis. The we introduce the neutrosophic system that is a quasi or (t,i,f) classical system, ...