Adaptive Reinforcement Learning through Evolving Self-Modifying Neural Networks

by   Samuel Schmidgall, et al.
George Mason University

The adaptive learning capabilities seen in biological neural networks are largely a product of the self-modifying behavior emerging from online plastic changes in synaptic connectivity. Current methods in Reinforcement Learning (RL) only adjust to new interactions after reflection over a specified time interval, preventing the emergence of online adaptivity. Recent work addressing this by endowing artificial neural networks with neuromodulated plasticity have been shown to improve performance on simple RL tasks trained using backpropagation, but have yet to scale up to larger problems. Here we study the problem of meta-learning in a challenging quadruped domain, where each leg of the quadruped has a chance of becoming unusable, requiring the agent to adapt by continuing locomotion with the remaining limbs. Results demonstrate that agents evolved using self-modifying plastic networks are more capable of adapting to complex meta-learning learning tasks, even outperforming the same network updated using gradient-based algorithms while taking less time to train.


Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning

In meta-learning, networks are trained with external algorithms to learn...

Meta-Learning through Hebbian Plasticity in Random Networks

Lifelong learning and adaptability are two defining aspects of biologica...

Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity

The impressive lifelong learning in animal brains is primarily enabled b...

Self-Adaptive Driving in Nonstationary Environments through Conjectural Online Lookahead Adaptation

Powered by deep representation learning, reinforcement learning (RL) pro...

Offline Meta-Reinforcement Learning for Industrial Insertion

Reinforcement learning (RL) can in principle make it possible for robots...

Training Larger Networks for Deep Reinforcement Learning

The success of deep learning in the computer vision and natural language...

Time Adaptive Reinforcement Learning

Reinforcement learning (RL) allows to solve complex tasks such as Go oft...

Please sign up or login with your details

Forgot password? Click here to reset