Goal babbling with unknown ranges: A direction-sampling approach

Reimann, Matthias

doi:10.1109/devlrn.2013.6652526

Cited by 18 publications

(21 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We design the scalar reward dependent upon the Euclidean distance from the goal such that it has a high negative value for distances further away from the goal that progressively but discretely decreases towards target, where it receives a reward of 0. The motivation behind this reward structure is to enable the robotic arm to make goal-directed attempts [22]. The episode will end either when the goal is reached or the maximum number of trials per episode are reached.…”

Section: B Reward-guided Actor-critic Architecturementioning

confidence: 99%

A Multiagent Reinforcement Learning approach for inverse kinematics of high dimensional manipulators with precision positioning

Ansari

Falotico

Mollard

et al. 2016

2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics (BioRob)

View full text Add to dashboard Cite

Flexible manipulators based on soft robotic technologies demonstrate compliance and dexterous maneuverability with virtually infinite degrees-of-freedom. Such systems have great potential in assistive and surgical fields where safe human-robot interaction is a prime concern. However, in order to enable practical application in these environments, intelligent control frameworks are required that can automate low-level sensorimotor skills to reach targets with high precision. We designed a novel motor learning algorithm based on cooperative Multi-Agent Reinforcement Learning that enables high-dimensional manipulators to exploit an abstracted state-space through a reward-guided mechanism to find solutions that have a guaranteed precision. We test our algorithm on a simulated planar 6-DOF with a discrete action-set and show that the all the points reached by the manipulator average an accuracy of 0.0056m (±0.002). The algorithm was found to be repeatable. We further validated our concept on the Baxter robotic arm to generate solutions up to 0.008m, exceptions being the joint angle accuracy and calibration of the robot

show abstract

Section: B Reward-guided Actor-critic Architecturementioning

confidence: 99%

A Multiagent Reinforcement Learning approach for inverse kinematics of high dimensional manipulators with precision positioning

Ansari

Falotico

Mollard

et al. 2016

2016 6th IEEE International Conference on Biomedical Robotics and Biomechatronics (BioRob)

View full text Add to dashboard Cite

show abstract

“…Many other exploration strategies could be easily integrated into the library, as for example Direction Sampling [7], compression progress [4], empowerment [8] and thus be compared in a proper way on various sensorimotor systems and using various sensorimotor internal models.…”

Section: Discussionmentioning

confidence: 99%

Explauto: an open-source Python library to study autonomous exploration in developmental robotics

Moulin-Frier

Rouanet

Oudeyer

2014

4th International Conference on Development and Learning and on Epigenetic Robotics

View full text Add to dashboard Cite

“…The underlying algorithm for the exploration is goal babbling, a method for bootstrapping an inverse model for a motor coordination task [7], [23], [24], [8]. Goal babbling operates in the space of outcomes.…”

Section: B Goal-directed Explorationmentioning

confidence: 99%

Hyperarticulation aids learning of new vowels in a developmental speech acquisition model

Philippsen

Reinhart

Wrede

et al. 2017

2017 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Abstract-Many studies emphasize the importance of infantdirected speech: stronger articulated, higher-quality speech helps infants to better distinguish different speech sounds. This effect has been widely investigated in terms of the infant's perceptual capabilities, but few studies examined whether infantdirected speech has an effect on articulatory learning.In earlier studies, we developed a model that learns articulatory control for a 3D vocal tract model via goal babbling. Exploration is organized in the space of outcomes. This so called goal space is generated from a set of ambient speech sounds. Similarly to how speech from the environment shapes infant's speech perception, the data from which the goal space is learned shapes the later learning process: it determines which sounds the model is able to discriminate, and thus, which sounds it can eventually learn to produce.We investigate how speech sound quality in early learning affects the model's capability to learn new vowel sounds. The model is trained either on hyperarticulated (tense) or on hypoarticulated (lax) vowels. Then we retrain the model with vowels from the other set.Results show that new vowels can be acquired although they were not included in early learning. There is, however, an effect of learning order, showing that models first trained on the stronger articulated tense vowels easier accommodate to new vowel sounds later on.

show abstract

Goal babbling with unknown ranges: A direction-sampling approach

Cited by 18 publications

References 19 publications

A Multiagent Reinforcement Learning approach for inverse kinematics of high dimensional manipulators with precision positioning

A Multiagent Reinforcement Learning approach for inverse kinematics of high dimensional manipulators with precision positioning

Explauto: an open-source Python library to study autonomous exploration in developmental robotics

Hyperarticulation aids learning of new vowels in a developmental speech acquisition model

Contact Info

Product

Resources

About