Fast Online Reinforcement Learning Control Using State-Space Dimensionality Reduction

State Space Reduction For Hierarchical Reinforcement Learning

This paper provides new techniques for abstracting the state space of a Markov Decision Process (MDP). These techniques extend one of the recent minimization models, known as -reduction, to construct a partition space that has a smaller number of states than the original MDP. As a result, learning policies on the partition space should be faster than on the original state space. The technique p...

Adaptive State-Space Quantisation and Multi-Task Reinforcement Learning Using . . .

Characterization and Control of Hysteretic Dynamics Using Online Reinforcement Learning

Hysteretic dynamical systems are challenging to control due to their hard nonlinearity and difficulty in modeling. One type of systemwith hysteretic dynamics that is gaining use in aerospace systems is the shape-memory alloy-based actuator. These actuators provide aircraft and spacecraft systems with the ability to achieve component-level or vehicle-level geometry or shape changes. Characteriza...

State-space Dimensionality Reduction in Markov Decision Processes

Learning of autonomous agents during their interaction with the environment is one of the frequent tasks in machine learning. However, the efficiency of the learning process drops dramatically with the complexity of the problem domain. In this paper, we present a survey of existing methods for reduction of the dimensionality. These methods can help find efficient solutions to the reinforcement ...

Mobile Agent Control in Intelligent Space using Reinforcement Learning

Finding the safest shortest path in an unknown environment is a fundamental task in mobile robotics. To emulate the human adaptibility in this field, we can use the Intelligent Space concept. The Intelligent Space is a distributed sensory system, which is the background infrastructure to observe human walking in a limited area. The observation of human beings is applied to create a walkable are...