Limits...
Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics.

Burms J, Caluwaerts K, Dambre J - Front Neurorobot (2015)

Bottom Line: Our results demonstrate the universal applicability of reward-modulated Hebbian learning.Furthermore, they demonstrate the robustness of systems trained with the learning rule.This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics.

View Article: PubMed Central - PubMed

Affiliation: Computing Systems Laboratory (Reservoir Team), Electronics and Information Systems Department (ELIS), Ghent University , Ghent , Belgium.

ABSTRACT
In embodied computation (or morphological computation), part of the complexity of motor control is offloaded to the body dynamics. We demonstrate that a simple Hebbian-like learning rule can be used to train systems with (partial) embodiment, and can be extended outside of the scope of traditional neural networks. To this end, we apply the learning rule to optimize the connection weights of recurrent neural networks with different topologies and for various tasks. We then apply this learning rule to a simulated compliant tensegrity robot by optimizing static feedback controllers that directly exploit the dynamics of the robot body. This leads to partially embodied controllers, i.e., hybrid controllers that naturally integrate the computations that are performed by the robot body into a neural network architecture. Our results demonstrate the universal applicability of reward-modulated Hebbian learning. Furthermore, they demonstrate the robustness of systems trained with the learning rule. This study strengthens our belief that compliant robots should or can be seen as computational units, instead of dumb hardware that needs a complex controller. This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics.

No MeSH data available.


Related in: MedlinePlus

Overview of task 3: the network has to reproduce part of the first input (black line) in reverse at the end of the trial (dashed blue line). More precisely, the first 5 steps of the first input are to be reproduced in reverse at the end of the trial (12 time steps total). The input space consists of a straight line originating and ending in [0, 1]. A second input indicates when the network has to start producing the desired observations.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4538293&req=5

Figure 3: Overview of task 3: the network has to reproduce part of the first input (black line) in reverse at the end of the trial (dashed blue line). More precisely, the first 5 steps of the first input are to be reproduced in reverse at the end of the trial (12 time steps total). The input space consists of a straight line originating and ending in [0, 1]. A second input indicates when the network has to start producing the desired observations.

Mentions: The task at hand is to reproduce part of the input in reverse after a delay (see Figure 3).


Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics.

Burms J, Caluwaerts K, Dambre J - Front Neurorobot (2015)

Overview of task 3: the network has to reproduce part of the first input (black line) in reverse at the end of the trial (dashed blue line). More precisely, the first 5 steps of the first input are to be reproduced in reverse at the end of the trial (12 time steps total). The input space consists of a straight line originating and ending in [0, 1]. A second input indicates when the network has to start producing the desired observations.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4538293&req=5

Figure 3: Overview of task 3: the network has to reproduce part of the first input (black line) in reverse at the end of the trial (dashed blue line). More precisely, the first 5 steps of the first input are to be reproduced in reverse at the end of the trial (12 time steps total). The input space consists of a straight line originating and ending in [0, 1]. A second input indicates when the network has to start producing the desired observations.
Mentions: The task at hand is to reproduce part of the input in reverse after a delay (see Figure 3).

Bottom Line: Our results demonstrate the universal applicability of reward-modulated Hebbian learning.Furthermore, they demonstrate the robustness of systems trained with the learning rule.This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics.

View Article: PubMed Central - PubMed

Affiliation: Computing Systems Laboratory (Reservoir Team), Electronics and Information Systems Department (ELIS), Ghent University , Ghent , Belgium.

ABSTRACT
In embodied computation (or morphological computation), part of the complexity of motor control is offloaded to the body dynamics. We demonstrate that a simple Hebbian-like learning rule can be used to train systems with (partial) embodiment, and can be extended outside of the scope of traditional neural networks. To this end, we apply the learning rule to optimize the connection weights of recurrent neural networks with different topologies and for various tasks. We then apply this learning rule to a simulated compliant tensegrity robot by optimizing static feedback controllers that directly exploit the dynamics of the robot body. This leads to partially embodied controllers, i.e., hybrid controllers that naturally integrate the computations that are performed by the robot body into a neural network architecture. Our results demonstrate the universal applicability of reward-modulated Hebbian learning. Furthermore, they demonstrate the robustness of systems trained with the learning rule. This study strengthens our belief that compliant robots should or can be seen as computational units, instead of dumb hardware that needs a complex controller. This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics.

No MeSH data available.


Related in: MedlinePlus