Visual Transfer for Reinforcement Learning via Wasserstein Domain Confusion
Not on the map. Why?
Abstract (arXiv)
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 two instantiations of 16 OpenAI Procgen environments.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jun 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 0; 2023: 3.
5 papers.
- 2021Decoupling Value and Policy for Generalization in Reinforcement Learningcited by 81
- 2023On the Importance of Exploration for Generalization in Reinforcement Learningcited by 30
- 2023The Generalization Gap in Offline Reinforcement Learningcited by 25
- 2021Domain Adversarial Reinforcement Learningcited by 19
- 2023P3O: Transferring Visual Representations for Reinforcement Learning via Promptingcited by 1
- 2023The Generalization Gap in Offline Reinforcement Learning10 Dec 2023
- 2023On the Importance of Exploration for Generalization in Reinforcement Learning8 Jun 2023
- 2023P3O: Transferring Visual Representations for Reinforcement Learning via Prompting22 Mar 2023
- 2021Decoupling Value and Policy for Generalization in Reinforcement Learning20 Feb 2021
- 2021Domain Adversarial Reinforcement Learning14 Feb 2021