object-oriented MDP

COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning …
Loic Matthey, Nicholas Watters, Matko Bosnjak, Christopher P Burgess, Alexander Lerchner
PDF Cite Code Twitter thread explainer
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration