This article describes the development of reinforcement learning within the Sigma graphical cognitive architecture. Reinforcement learning has been deconstructed in terms of the interactions among more basic mechanisms and knowledge in Sigma, making it a derived capability rather than a de novo mechanism. Basic reinforcement learning – both model-based and model-free – are demonstrated, along w...

Computer games are challenging test beds for machine learning research. Without applying abstraction and generalization techniques, many traditional machine learning techniques, such as reinforcement learning, will fail to learn efficiently. In this paper we examine extensions of reinforcement learning that scale to the complexity of computer games. In particular we look at hierarchical reinfor...

Learning complex skills is driven by reinforcement, which facilitates both online within-session gains and retention of the acquired skills. Yet, in ecologically relevant situations, skills are often acquired when mapping between actions and rewarding outcomes is unknown to the learning agent, resulting in reinforcement schedules of a stochastic nature. Here we trained subjects on a visuomotor ...

To behave adaptively, we must learn from the consequences of our actions. Doing so is difficult when the consequences of an action follow a delay. This introduces the problem of temporal credit assignment. When feedback follows a sequence of decisions, how should the individual assign credit to the intermediate actions that comprise the sequence? Research in reinforcement learning provides 2 ge...

This paper implements a Neuro-Fuzzy (FNN) approach to autonomously navigate a car-like robot in an unknown environment. The applied technique allows the robot to avoid obstacles and locally search for a path leading to the goal after learning and adaptation. It is based on two Fuzzy Artmap neural networks, a Reinforcement trial and error neural network and a Mamdani fuzzy logic controller (FLC)...

This paper proposes a new fuzzy neural network based reinforcement adaptive iterative learning controller for a class of nonlinear systems. Different from some existing reinforcement learning schemes, the reinforcement adaptive iterative learning controller has the advantages of rigorous proofs without using an approximation of the plant Jacobian. The critic is appended into the reinforcement a...

In this paper, we analyze and compare general development and individual behavior on two non-profit internet-based hospitality exchange services – bewelcome.org and warmshowers.org. We measure the effort needed to achieve a reallife interaction, whereby the advantages of mutual altruism arise. The effort needed is the communication quantified in units of time. Since the amount of effort is not ...

A new algorithm for reinforcement learning, advantage updating, is described. Advantage updating is a direct learning technique; it does not require a model to be given or learned. It is incremental, requiring only a constant amount of calculation per time step, independent of the number of possible actions, possible outcomes from a given action, or number of states. Analysis and simulation ind...