Playing Games in the Dark: An approach for cross-modality transfer in reinforcement learning

November 28, 2019 Β· Declared Dead Β· πŸ› Adaptive Agents and Multi-Agent Systems

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Rui Silva, Miguel Vasco, Francisco S. Melo, Ana Paiva, Manuela Veloso arXiv ID 1911.12851 Category cs.AI: Artificial Intelligence Cross-listed cs.LG Citations 15 Venue Adaptive Agents and Multi-Agent Systems Last Checked 4 months ago
Abstract
In this work we explore the use of latent representations obtained from multiple input sensory modalities (such as images or sounds) in allowing an agent to learn and exploit policies over different subsets of input modalities. We propose a three-stage architecture that allows a reinforcement learning agent trained over a given sensory modality, to execute its task on a different sensory modality-for example, learning a visual policy over image inputs, and then execute such policy when only sound inputs are available. We show that the generalized policies achieve better out-of-the-box performance when compared to different baselines. Moreover, we show this holds in different OpenAI gym and video game environments, even when using different multimodal generative models and reinforcement learning algorithms.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted