May 22, 2019 · Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models.
May 22, 2019 · Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep re- inforcement learning algorithms.
This Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of ...
Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its ...
Data efficiency and robustness to task-irrelevant perturbations arelong-standing challenges for deep reinforcement learning algorithms.
This environment was developed for the COBRA agent introduced in the paper "COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and ...
May 28, 2019 · COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration https://buff.ly/2M9LFCk #ai ...
[5] Watters, Nicholas, et al. “Cobra: Data-efficient model-based rl through unsupervised object discovery and curiosity-driven exploration.” arXiv preprint ...
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration · 1 code implementation • 22 May 2019 • Nicholas ...
Cobra: Data-efficient model-based rl through unsupervised object discovery and curiosity-driven exploration. N Watters, L Matthey, M Bosnjak, CP Burgess, A ...