A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Disentangling Controllable Object through Video Prediction Improves Visual Reinforcement Learning
[article]
2020
arXiv
pre-print
In many vision-based reinforcement learning (RL) problems, the agent controls a movable object in its visual field, e.g., the player's avatar in video games and the robotic arm in visual grasping and manipulation. Leveraging action-conditioned video prediction, we propose an end-to-end learning framework to disentangle the controllable object from the observation signal. The disentangled representation is shown to be useful for RL as additional observation channels to the agent. Experiments on
arXiv:2002.09136v1
fatcat:bw3iyw3gnfhtlldylcxxdwcb7e