Disentangling Controllable Object through Video Prediction Improves Visual Reinforcement Learning
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... (read more)
PDFTasks
Datasets
Arcade Learning Environment
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Experience Replay
Double Q-learning
Q-Learning
Double DQN
Dense Connections
Convolution
DQN