We consider reinforcement learning as solving a Markov decision process with unknown transition distribution. Based on interaction with the environment, an estimate of the transit...
Abstract. Greedy machine learning algorithms suffer from shortsightedness, potentially returning suboptimal models due to limited exploration of the search space. Greedy search mis...
Recently, opening the learner model to the learner it represents has become more common in adaptive learning environments. There have also been systems that allow instructors acces...
Susan Bull, Andrew Mabbott, Abdallatif S. Abu-Issa
In this paper we report on using a relational state space in multi-agent reinforcement learning. There is growing evidence in the Reinforcement Learning research community that a r...
Tom Croonenborghs, Karl Tuyls, Jan Ramon, Maurice ...
This paper presents a novel framework called proto-reinforcement learning (PRL), based on a mathematical model of a proto-value function: these are task-independent basis function...