Andre Barreto

TL;DR: This work proposes a transfer framework for the scenario where the reward function changes between tasks but the environment's dynamics remain the same, and derives two theorems that set the approach in firm theoretical ground and presents experiments that show that it successfully promotes transfer in practice.

TL;DR: This article proposed a transfer framework for the scenario where the reward function changes between tasks but the environment's dynamics remain the same, and derived two theorems that set their approach in firm theoretical ground and present experiments that show that it successfully promotes transfer in practice, significantly outperforming alternative methods in a sequence of navigation tasks and in the control of a simulated robotic arm.

TL;DR: In this paper, the authors introduce the predictron architecture, which consists of a fully abstract model, represented by a Markov reward process, that can be rolled forward multiple "imagined" planning steps.

TL;DR: The predictron consists of a fully abstract model, represented by a Markov reward process, that can be rolled forward multiple "imagined" planning steps that accumulates internal rewards and values over multiple planning depths.

TL;DR: This paper shows that the transfer promoted by SFs & GPI leads to very good policies on unseen tasks almost instantaneously, and describes how to learn policies specialised to the new tasks in a way that allows them to be added to the agent's set of skills, and thus be reused in the future.