[robotics-worldwide] Reminder: CfP - RSS 2013 Workshop on "Hierarchical and Structured Learning for Robotics "
neumann at ias.tu-darmstadt.de
Mon May 27 08:03:17 PDT 2013
REMINDER --- SECOND CALL FOR POSTERS
RSS 2013 WORKSHOP ON "Hierarchical and Structured Learning for Robotics"
Title: Hierarchical and Structured Learning for Robotics
Gerhard Neumann (neumann at ias.tu-darmstadt.de, TU Darmstadt)
George Konidaris (gdk at csail.mit.edu, MIT Computer Science and Artificial
Freek Stulp (freek.stulp at ensta-paristech.fr, ENSTA - ParisTech)
Jan Peters (peters at ias.tu-darmstadt.de, TU Darmstadt and MPI for
Learning robot control policies in complex real-world environments is a
major challenge for machine learning due to the inherent high
dimensionality, partial observability and the high costs of data
generation. Treating robot learning as a monolithic machine problem and
employing off-the-shelf approaches is unrealistic at best. However, the
physical world can yield important insights into the inherent structure
of control policies, state or action spaces and reward functions. For
example, many robot motor tasks are also hierarchically structured
decision tasks. For example, a tennis playing robot has to combine
different striking movements sequentially. During locomotion there are
at least three behaviors simultaneously active as a robot has to combine
its gait generation with foot placement and balance control. First
domain-driven skill learning approaches have already yielded impressive
recent successes by incorporating such structural insights into the
learning process. Hence, a promising route to more scalable policy
learning approaches includes the automatic exploitation of the
environment's structure, resulting in new structured learning approaches
for robot control.
Structured and hierarchical learning has been an important trend in
machine learning in recent years. In robotics, researchers often ended
up naturally at well-structured hierarchical policies based on
discrete-continuous partitions (e.g., define local movement generators
as well as a prioritized operational space control for combining them)
with nested control loops at several different speeds (i.e., fast
control loops for smooth and accurate movement achievement, slower loops
for model-predictive planning). Furthermore, evidence from the fields
cognitive sciences indicate that humans also heavily exploit such
structures and hierarchies. Although such structures have been found in
human motor control, are favored in robot control and exist in machine
learning, the connections between these fields have not been well
explored. Transferring insights from structured prediction methods,
which make use of the inherent correlation in the data, to hierarchical
robot skill learning may be a crucial step. General approaches for
bringing structured policies, states, actions and rewards into robot
reinforcement learning may well be the key to tackle many challenges of
real-world robot environments and an important step to the vision of
intelligent autonomous robots which can learn rich and versatile sets of
motor skills. This workshop aims to reveal how complex motor skills
typically exhibit structures that can be exploited for learning reward
functions and to find structure in the state or action space.
In order to make progress towards the goal of structured learning for
robot control, this workshop aims at researchers from different machine
learning areas (such as reinforcement learning, structured prediction),
robotics and related disciplines (e.g., control engineering, and the
We particularly want to focus on the following important topics for
structured robot learning which have a big overlap from several of these
- Efficient representations and learning methods for hierarchical
- Learning in several layers of hierarchy
- Structured representations for motor control and planning
- Skill extraction and skill transfer
- Sequencing and composition of behaviors
- Hierarchical Bayesian Models for decision making and efficient
- Low-dimensional manifolds as structured representations for
- Exploiting correlations in the decision making process
- Prioritized control policies in a multi-task reinforcement
These challenges are important steps to building intelligent autonomous
robots and may potentially motivate new research topics in the related
The aim of this workshop is to bring together researchers which are
in structured representations, reinforcement learning, hierarchical
learning methods and control architectures.
Among these general topics we will focus on the following questions:
- How to efficiently use graphical models such as Markov random
fields to exploit correlations in the decision making process?
- How to extract the relevant structure (e.g. low dimensional
manifolds, factorizations...) from the state and action space?
- Can we efficiently model structure in the reward function or the
- How to learn good features for the policy or the value function?
- What can we learn from structured prediction?
Representations of behavior:
- What are good representations for motor skills?
- How can we efficiently reuse skills in new situations?
- How can we extract movement skills and elemental movements from
- How can we compose skills to solve a combination of tasks?
- How can we represent versatile motor skills?
- How can we represent and exploit the correlations over time in
the decision process?
- How to efficiently use structured representations for planning
- Can we learn task-priorities and use similar policies as in
- How to decompose optimal control laws into elemental movements ?
- How to use low-dimensional manifolds to control high-dimensional,
- Can we use chain or tree-like structures as policy representation
to mimic the kinematic structure of the
Hierarchical Learning Methods:
- How can we efficiently apply abstractions to the control problem?
- How to efficiently learn at several layers of hierarchy?
- Which policy search algorithms are appropriate for which
- Can we use hierarchical inverse reinforcement learning to acquire
skill reward functions, and priors over selecting those skills?
- How can we decide when to create new skills or re-use known ones?
- How can we discover and generalize important sub-goals in our
- How can we efficiently transfer skills to new situations?
- Can we use hierarchical Bayesian models to learn in
several layers of abstraction also in decision making?
- How to transfer learned models or even value functions to new tasks?
June 1st - Deadline of submission for Posters
June 4th - Notification of Poster Acceptance
Extended abstracts (1 pages) will be reviewed by the program committee
members on the basis of relevance, significance, and clarity. Accepted
contributions will be presented as posters but particularly exciting
work may be considered for talks. Submissions should be formatted
according to the conference templates and submitted via email to
neumann at ias.tu-darmstadt.de.
Gerhard Neumann, Technische Universitaet Darmstadt
George Konidaris, MIT Computer Science and Artificial Intelligence
Freek Stulp, ENSTA - ParisTech
Jan Peters, Technische Universitaet Darmstadt and Max Planck Institute
for Intelligent Systems
LOCATION AND MORE INFORMATION
The most up-to-date information about the workshop can be found on the
RSS 2013 webpage.
More information about the robotics-worldwide