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

Evolution of the reward and the spectral radius for the 2-bit delayed XOR task (left) and the 3-bit decoder task (right). The plots show the average, best, and worst rewards and the average spectral radius out of 10 runs. Each run has different random initializations and input sequences.
© Copyright Policy
Related In: Results  -  Collection

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

Figure 6: Evolution of the reward and the spectral radius for the 2-bit delayed XOR task (left) and the 3-bit decoder task (right). The plots show the average, best, and worst rewards and the average spectral radius out of 10 runs. Each run has different random initializations and input sequences.

Mentions: Figure 6 shows the evolution of the reward and the spectral radius for the discrete input tasks (tasks 1 and 2). We performed 10 runs with different random initializations and input sequences. For both tasks, and for every run, we observe that the network indeed learns to solve the task almost perfectly, as the rewards converge to their maximal value of 0.


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

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

Evolution of the reward and the spectral radius for the 2-bit delayed XOR task (left) and the 3-bit decoder task (right). The plots show the average, best, and worst rewards and the average spectral radius out of 10 runs. Each run has different random initializations and input sequences.
© Copyright Policy
Related In: Results  -  Collection

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

Figure 6: Evolution of the reward and the spectral radius for the 2-bit delayed XOR task (left) and the 3-bit decoder task (right). The plots show the average, best, and worst rewards and the average spectral radius out of 10 runs. Each run has different random initializations and input sequences.
Mentions: Figure 6 shows the evolution of the reward and the spectral radius for the discrete input tasks (tasks 1 and 2). We performed 10 runs with different random initializations and input sequences. For both tasks, and for every run, we observe that the network indeed learns to solve the task almost perfectly, as the rewards converge to their maximal value of 0.

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