Visual Transfer For Reinforcement Learning Via Wasserstein Domain Confusion
| Autor: | Josh Roy, George D. Konidaris |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Proceedings of the AAAI Conference on Artificial Intelligence. 35:9454-9462 |
| ISSN: | 2374-3468 2159-5399 |
| DOI: | 10.1609/aaai.v35i11.17139 |
| Popis: | We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO), a novel algorithm for visual transfer in Reinforcement Learning that explicitly learns to align the distributions of extracted features between a source and target task. WAPPO approximates and minimizes the Wasserstein-1 distance between the distributions of features from source and target domains via a novel Wasserstein Confusion objective. WAPPO outperforms the prior state-of-the-art in visual transfer and successfully transfers policies across Visual Cartpole and both the easy and hard settings of of 16 OpenAI Procgen environments. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|