5 papers
RANDPOL: Parameter-Efficient End-to-End Quadruped Locomotion via Randomized Policy Learning
Zhuochen Liu, Rahul Jain, Quan Nguyen
Modern learning-based locomotion controllers typically rely on fully trainable deep neural networks with a large number of parameters. This paper studies a different design point f…
Almost Sure Convergence of Stochastic Approximation: An Interplay of Noise and Step Size
Quang Dinh Thien Nguyen, Duc Anh Nguyen, Hoang Huy Nguyen +1
We study the almost sure convergence of the Stochastic Approximation algorithm to the fixed point of a nonlinear operator under a negative drift condition and a general n…
How to Set in Adam: An Online Learning Perspective
Quan Nguyen
While Adam is one of the most effective optimizer for training large-scale machine learning models, a theoretical understanding of how to optimally set its momentum factors, …
Preferenced Oracle Guided Multi-mode Policies for Dynamic Bipedal Loco-Manipulation
Prashanth Ravichandar, Lokesh Krishna, Nikhil Sobanbabu +1
Dynamic loco-manipulation calls for effective whole-body control and contact-rich interactions with the object and the environment. Existing learning-based control synthesis relies…
DiffCoTune: Differentiable Co-Tuning for Cross-domain Robot Control
Lokesh Krishna, Sheng Cheng, Junheng Li +2
The deployment of robot controllers is hindered by modeling discrepancies due to necessary simplifications for computational tractability or inaccuracies in data-generating simulat…