A liveness-based Bellman operator enables conservative offline policy evaluation for manipulation tasks by encoding task progression and reducing truncation bias from finite horizons.
Dex- terous manipulation with deep reinforcement learning: Efficient, gen- eral, and low-cost, in: 2019 International Conference on Robotics and Automation (ICRA), pp
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
A conformal prediction certification for belief-space safety filters focuses verification on reliable inference regions to produce less conservative yet high-probability safe filters than standard baselines in human-vehicle simulations.
A VAE-based latent task representation enables automatic curriculum generation in CRL for non-Euclidean navigation tasks, outperforming interpolation and GAN-based methods in experiments.
Physical admissibility is defined as a prediction-control interface using kinematic, dynamic, and composed-horizon conditions to reject invalid dynamics proposals, with AUC 0.957 on LeRobot PushT and 87-89% prevention of invalid actions in interventions.
citing papers explorer
-
Curriculum reinforcement learning with measurable task representation learning
A VAE-based latent task representation enables automatic curriculum generation in CRL for non-Euclidean navigation tasks, outperforming interpolation and GAN-based methods in experiments.