DeepAI AI Chat
Log In Sign Up

Learning to Explore in Motion and Interaction Tasks

08/10/2019
by   Miroslav Bogdanovic, et al.
1

Model free reinforcement learning suffers from the high sampling complexity inherent to robotic manipulation or locomotion tasks. Most successful approaches typically use random sampling strategies which leads to slow policy convergence. In this paper we present a novel approach for efficient exploration that leverages previously learned tasks. We exploit the fact that the same system is used across many tasks and build a generative model for exploration based on data from previously solved tasks to improve learning new tasks. The approach also enables continuous learning of improved exploration strategies as novel tasks are learned. Extensive simulations on a robot manipulator performing a variety of motion and contact interaction tasks demonstrate the capabilities of the approach. In particular, our experiments suggest that the exploration strategy can more than double learning speed, especially when rewards are sparse. Moreover, the algorithm is robust to task variations and parameter tuning, making it beneficial for complex robotic problems.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/20/2018

Meta-Reinforcement Learning of Structured Exploration Strategies

Exploration is a fundamental challenge in reinforcement learning (RL). M...
10/23/2022

Active Exploration for Robotic Manipulation

Robotic manipulation stands as a largely unsolved problem despite signif...
03/19/2018

Composable Deep Reinforcement Learning for Robotic Manipulation

Model-free deep reinforcement learning has been shown to exhibit good pe...
11/17/2021

Self-Learning Tuning for Post-Silicon Validation

Increasing complexity of modern chips makes design validation more diffi...
02/22/2021

Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivation

In this paper we address the challenge of exploration in deep reinforcem...
12/21/2018

NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning

Reinforcement learning agents need exploratory behaviors to escape from ...
04/22/2019

Exploration of Self-Propelling Droplets Using a Curiosity Driven Robotic Assistant

We describe a chemical robotic assistant equipped with a curiosity algor...