We present a framework for transfer in reinforcement learning based on the idea that related
tasks share some common features, and that transfer can be achieved via those shared …

A suitable state representation is a fundamental part of the learning process in
Reinforcement Learning. In various tasks, the state can either be described by natural …

Abstract The Qualitative Rectilinear Projection Calculus (QRPC), a new representation
model based on planar trajectories, is presented in this work for describing qualitatively …

Reinforcement learning has developed as a successful learning approach for domains that
are not fully understood and that are too complex to be described in closed form. However …

In this article we investigate the role of abstraction principles for knowledge transfer in agent
control learning tasks. We analyze abstraction from a formal point of view and characterize …

Navigation based on detected landmarks is an important facet of robot navigation. This work
investigates into a qualitative representation of landmarks for an autonomous learning task …

Learning and planning are powerful AI methods that exhibit complementary strengths. While
planning allows goal-directed actions to be computed when a reliable forward model is …

It is often hard for a reinforcement learning (RL) agent to utilize previous experience to solve
new similar but more complex tasks. In this research, we combine the transfer learning with …

We investigate the problem of learning the control of small groups of units in combat
situations in Real Time Strategy (RTS) games. AI systems may acquire such skills by …

The qualification problem is well known within the field of artificial intelligence. This paper
introduced a specific aspect of qualification problem that deals with knowing the possibility …