Trajectory-based data augmentation exploits geometric relationships between rewards, values, and logging policies to enable effective offline RL from few suboptimal trajectories.
In: 2018 IEEE International Conference on Robotics and Automation (ICRA)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Soft growing robots map unknown 2D environments by characterizing collision deformations, building a geometry-based simulator, and using Monte Carlo sampling to select optimal deployments that approach ideal actions.
citing papers explorer
-
Trajectory-Level Data Augmentation for Offline Reinforcement Learning
Trajectory-based data augmentation exploits geometric relationships between rewards, values, and logging policies to enable effective offline RL from few suboptimal trajectories.
-
Linking Exteroception and Proprioception through Improved Contact Modeling for Soft Growing Robots
Soft growing robots map unknown 2D environments by characterizing collision deformations, building a geometry-based simulator, and using Monte Carlo sampling to select optimal deployments that approach ideal actions.