papers AI Learner
The Github is limit! Click to go to the new site.

Transferring Agent Behaviors from Videos via Motion GANs

2017-11-21
Ashley D. Edwards, Charles L. Isbell Jr

Abstract

A major bottleneck for developing general reinforcement learning agents is determining rewards that will yield desirable behaviors under various circumstances. We introduce a general mechanism for automatically specifying meaningful behaviors from raw pixels. In particular, we train a generative adversarial network to produce short sub-goals represented through motion templates. We demonstrate that this approach generates visually meaningful behaviors in unknown environments with novel agents and describe how these motions can be used to train reinforcement learning agents.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1711.07676

PDF

https://arxiv.org/pdf/1711.07676


Similar Posts

Comments