A Transfer Learning Approach for Deep Reinforcement Learning

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and more.Subscribe

CC BY

Source arXiv

Machine Learning

Artificial Intelligence

A Transfer Learning Approach for Deep Reinforcement Learning

Component Transfer Learning for Deep RL Based on Abstract Representations

We investigate a specific transfer learning approach for deep reinforcement learning in the context where the internal dynamics between two tasks are the same but the visual representations differ.

We learn a low-dimensional encoding of the environment, meant to capture summarizing abstractions, from which the internal dynamics and value functions are learned.

Transfer is then obtained by freezing the learned internal dynamics and value functions, thus reusing the shared low-dimensional embedding space.

When retraining the encoder for transfer, we make several observations : (i) in some cases, there are local minima that have small losses but a mismatching embedding space, resulting in poor task performance and (ii) in the absence of local minima, the output of the encoder converges in our experiments to the same embedding space, which leads to a fast and efficient transfer as compared to learning from scratch.

Authors

Geoffrey van Driessel, Vincent Francois-Lavet

◐ Recommended Follows

◐ Latest Activity