Abstract
Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that fine-tuning-the common transfer learning paradigm-fails to adapt to these changes, to the extent that it is faster to re-train the model from scratch. We show that by separating the visual transfer task from the control policy we achieve substantially better sample efficiency and transfer behavior, allowing an agent trained on the source task to transfer well to the target tasks. The visual mapping from the target to the source domain is performed using unaligned GANs, resulting in a control policy that can be further improved using imitation learning from imperfect demonstrations. We demonstrate the approach on synthetic visual variants of the Breakout game, as well as on transfer between subsequent levels of Road Fighter, a Nintendo car-driving game. A visualization of our approach can be seen in https://youtu.be/4mnkzYyXMn4 and https://youtu.be/KCGTrQi60go.
Original language | English |
---|---|
Title of host publication | 36th International Conference on Machine Learning, ICML 2019 |
Publisher | International Machine Learning Society (IMLS) |
Pages | 3623-3634 |
Number of pages | 12 |
ISBN (Electronic) | 9781510886988 |
State | Published - 2019 |
Event | 36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States Duration: 9 Jun 2019 → 15 Jun 2019 |
Publication series
Name | 36th International Conference on Machine Learning, ICML 2019 |
---|---|
Volume | 2019-June |
Conference
Conference | 36th International Conference on Machine Learning, ICML 2019 |
---|---|
Country/Territory | United States |
City | Long Beach |
Period | 9/06/19 → 15/06/19 |
Bibliographical note
Publisher Copyright:Copyright © 2019 ASME