Unsupervised Learning and Exploration of Reachable Outcome Space

Autor:	Paolo, Giuseppe, Laflaquière, Alban, Coninx, Alexandre, Doncieux, Stephane
Rok vydání:	2019
Předmět:	Computer Science - Robotics Computer Science - Artificial Intelligence Computer Science - Machine Learning Computer Science - Neural and Evolutionary Computing
Druh dokumentu:	Working Paper
Popis:	Performing Reinforcement Learning in sparse rewards settings, with very little prior knowledge, is a challenging problem since there is no signal to properly guide the learning process. In such situations, a good search strategy is fundamental. At the same time, not having to adapt the algorithm to every single problem is very desirable. Here we introduce TAXONS, a Task Agnostic eXploration of Outcome spaces through Novelty and Surprise algorithm. Based on a population-based divergent-search approach, it learns a set of diverse policies directly from high-dimensional observations, without any task-specific information. TAXONS builds a repertoire of policies while training an autoencoder on the high-dimensional observation of the final state of the system to build a low-dimensional outcome space. The learned outcome space, combined with the reconstruction error, is used to drive the search for new policies. Results show that TAXONS can find a diverse set of controllers, covering a good part of the ground-truth outcome space, while having no information about such space. Comment: Published at IEEE International Conference on Robotics and Automation (ICRA) 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1909.05508 Zobrazit plný text záznamu View this record from Arxiv