Adaptive Reinforcement Learning through Evolving Self-Modifying Neural Networks

05/22/2020
by   Samuel Schmidgall, et al.
1

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.

READ FULL TEXT
research
12/16/2021

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

In meta-learning, networks are trained with external algorithms to learn...
research
07/06/2020

Meta-Learning through Hebbian Plasticity in Random Networks

Lifelong learning and adaptability are two defining aspects of biologica...
research
02/24/2020

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

The impressive lifelong learning in animal brains is primarily enabled b...
research
10/06/2022

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

Powered by deep representation learning, reinforcement learning (RL) pro...
research
10/08/2021

Offline Meta-Reinforcement Learning for Industrial Insertion

Reinforcement learning (RL) can in principle make it possible for robots...
research
02/16/2021

Training Larger Networks for Deep Reinforcement Learning

The success of deep learning in the computer vision and natural language...
research
04/18/2020

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