12 papers
StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
Duy M. H. Nguyen, Tuan A. Tran, Duong Nguyen +17
Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-attention, often without retraining.…
Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
Christian Scherer, Joe Watson, Theo Gruner +3
Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for…
FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control
Donghu Kim, Youngdo Lee, Minho Park +10
Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Policy Optimization (PPO) are widely…
XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies
Daniel Palenicek, Florian Vogt, Joe Watson +3
For reinforcement learning in the real world online exploration is expensive A common practice in robotic reinforcement learning is to incorporate additional data to improve sample…
XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning
Daniel Palenicek, Florian Vogt, Joe Watson +2
Sample efficiency is a central property of effective deep reinforcement learning algorithms. Recent work has improved this through added complexity, such as larger models, exotic n…
Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion
Nico Bohlinger, Jonathan Kinzel, Daniel Palenicek +2
On-robot Reinforcement Learning is a promising approach to train embodiment-aware policies for legged robots. However, the computational constraints of real-time learning on robots…