Online robot guidance and navigation in non-stationary environment with hybrid Hierarchical Reinforcement Learning

Hierarchical Reinforcement Learning for Robot Navigation

For complex tasks, such as manipulation and robot navigation, reinforcement learning (RL) is well-known to be difficult due to the curse of dimensionality. To overcome this complexity and making RL feasible, hierarchical RL (HRL) has been suggested. The basic idea of HRL is to divide the original task into elementary subtasks, which can be learned using RL. In this paper, we propose a HRL archi...

Adaptive robot learning in a non-stationary environment

Adaptive control is challenging in real-world applications such as robotics. Learning has to be rapid enough to be performed in real time and to avoid damage to the robot. Models using linear function approximation are interesting in such tasks because they offer rapid learning and have small memory and processing requirements. This makes them suitable as adaptive controllers in nonstationary e...

Hierarchical Hybrid Reinforcement Learning Algorithms

Hierarchical Reinforcement Learning in Robot Control

The use of reinforcement learning in robotics suffers greatly from the curse of dimensionality, stemming from the necessity of a high DOF in a robot to solve even the simplest tasks. This paper gives an overview over several attempts to decrease this problem using a hierarchical structure of reinforcement learning, an evaluation of the problems that arise with such approaches and possible solut...

Reinforcement Learning in Nonstationary Environment Navigation Tasks

The field of reinforcement learning (RL) has achieved great strides in learning control knowledge from closed-loop interaction with environments. “Classical” RL, based on atomic state space representations, suffers from an inability to adapt to nonstationarities in the target Markov decision process (i.e., environment). Relational RL is widely seen as being a potential solution to this shortcom...