When applying reinforcement learning in domains with very large or continuous state
spaces, the experience obtained by the learning agent in the interaction with the …

One of the difficulties in reinforcement learning (RL) is that an optimal policy is acquired
through enormous trials. As a solution to reduce waste explorations in learning, recently the …

This thesis takes an empirical approach to understanding of the behavior and interactions
between the two main components of reinforcement learning: the learning algorithm and the …

Research in intelligent systems field has led to different learning methods for machines to
acquire knowledge, among them, reinforcement learning (RL). Given the problem of the time …

The paradigm of reinforcement learning provides an appealing framework for developing
intelligent adaptive systems. The learner interacts with a possibly unknown and stochastic …

This paper discusses a system that accelerates reinforcement learning by using transfer
from related tasks. Without such transfer, even if two tasks are very similar at some abstract …

Reinforcement learning is widely regarded as elegant in theory but hopelessly slow in
practice. This is because it is often studied under the assumption that there is little or no prior …

When applying a Reinforcement Learning technique to problems with continuous or very
large state spaces, some kind of generalization is required. In the bibliography, two main …

This paper discusses a method to accelerate reinforcement learning. A concept is firstly
defined, ie, the state space reduction conserving policy. An algorithm is then given, where …

This paper introduces the rllib as an original C++ template-based library oriented toward
value function estimation. Generic programming is promoted here as a way of having a good …