1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Disentangling Controllable Object Through Video Prediction Improves Visual Reinforcement Learning

Disentangling Controllable Object Through Video Prediction Improves Visual Reinforcement Learning

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

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 predi

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Disentangling Controllable Object Through Video Prediction Improves Visual Reinforcement Learning

00:12:54

0 views

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 predi