Smooth Exploration for Robotic Reinforcement Learning
Antonin Raffin (Deutsches Zentrum für Luft- und Raumfahrt (DLR))
Jens Kober (TU Delft - Learning & Autonomous Control)
Freek Stulp (Deutsches Zentrum für Luft- und Raumfahrt (DLR))
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Reinforcement learning (RL) enables robots to learn skills from interactions with the real world. In practice, the unstructured step-based exploration used in Deep RL – often very successful in simulation – leads to jerky motion patterns on real robots. Consequences of the resulting shaky behavior are poor exploration, or even damage to the robot. We address these issues by adapting state-dependent exploration (SDE) [1] to current Deep RL algorithms. To enable this adaptation, we propose two extensions to the original SDE, using more general features and re-sampling the noise periodically, which leads to a new exploration method generalized state-dependent exploration (gSDE). We evaluate gSDE both in simulation, on PyBullet continuous control tasks, and directly on three different real robots: a tendon-driven elastic robot, a quadruped and an RC car. The noise sampling interval of gSDE enables a compromise between performance and smoothness, which allows training directly on the real robots without loss of performance.