Learning by Playing - Solving Sparse Reward Tasks from Scratch

Autor:	Riedmiller, Martin, Hafner, Roland, Lampe, Thomas, Neunert, Michael, Degrave, Jonas, Van de Wiele, Tom, Mnih, Volodymyr, Heess, Nicolas, Springenberg, Jost Tobias
Rok vydání:	2018
Předmět:	Computer Science - Learning Computer Science - Robotics Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch - in the presence of multiple sparse reward signals. To this end, the agent is equipped with a set of general auxiliary tasks, that it attempts to learn simultaneously via off-policy RL. The key idea behind our method is that active (learned) scheduling and execution of auxiliary policies allows the agent to efficiently explore its environment - enabling it to excel at sparse reward RL. Our experiments in several challenging robotic manipulation settings demonstrate the power of our approach. Comment: A video of the rich set of learned behaviours can be found at https://youtu.be/mPKyvocNe_M
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1802.10567 Zobrazit plný text záznamu View this record from Arxiv