Q-map: a Convolutional Approach for Goal-Oriented Reinforcement Learning

ICLR 2019 Fabio Pardo • Vitaly Levdik • Petar Kormushev

Goal-oriented learning has become a core concept in reinforcement learning (RL), extending the reward signal as a sole way to define tasks. We show how this network can be efficiently trained with a 3D variant of Q-learning to update the estimates towards all goals at once. While the Q-map agent could be used for a wide range of applications, we propose a novel exploration mechanism in place of epsilon-greedy that relies on goal selection at a desired distance followed by several steps taken towards it, allowing long and coherent exploratory steps in the environment.

Full paper

Evaluation


No evaluation results yet. Help compare this paper to other papers by submitting the tasks and evaluation metrics from the paper.