research
∙
03/29/2022
Learning to Synthesize Volumetric Meshes from Vision-based Tactile Imprints
Vision-based tactile sensors typically utilize a deformable elastomer an...
share
research
∙
10/16/2021
Joint 3D Human Shape Recovery from A Single Imag with Bilayer-Graph
The ability to estimate the 3D human shape and pose from images can be u...
research
∙
08/05/2021
Lyapunov Robust Constrained-MDPs: Soft-Constrained Robustly Stable Policy Optimization under Model Uncertainty
Safety and robustness are two desired properties for any reinforcement l...
research
∙
05/20/2021
Cross-domain Imitation from Observations
Imitation learning seeks to circumvent the difficulty in designing prope...
research
∙
11/14/2020
Towards Human-Level Learning of Complex Physical Puzzles
Humans quickly solve tasks in novel systems with complex dynamics, witho...
research
∙
10/10/2020
Robust Constrained-MDPs: Soft-Constrained Robust Policy Optimization under Model Uncertainty
In this paper, we focus on the problem of robustifying reinforcement lea...
research
∙
11/03/2019
Learning from Trajectories via Subgoal Discovery
Learning to solve complex goal-oriented tasks with sparse terminal-only ...
research
∙
11/28/2018
Trajectory-based Learning for Ball-in-Maze Games
Deep Reinforcement Learning has shown tremendous success in solving seve...
research
∙
09/13/2018