11 papers
EMoE: Training-Free Expert Disagreement for Uncertainty-Aware Text-to-Image Diffusion
Lucas Berry, Axel Brando, Wei-Di Chang +2
Large text-to-image diffusion models rarely expose reliable signals of when a prompt is likely to produce a poorly aligned generation, especially when training data is undisclosed.…
Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning
Yash Jhaveri, Harley Wiltzer, Patrick Shafto +2
In the pursuit of finding an optimal policy, reinforcement learning (RL) methods generally ignore the properties of learned policies apart from their expected return. Thus, even wh…
VDFD: Multi-Agent Value Decomposition Framework with Disentangled World Model
Zhizun Wang, David Meger
In this paper, we propose a novel model-based multi-agent reinforcement learning approach named Value Decomposition Framework with Disentangled World Model to address the challenge…
Large Pre-Trained Models for Bimanual Manipulation in 3D
Hanna Yurchyk, Wei-Di Chang, Gregory Dudek +1
We investigate the integration of attention maps from a pre-trained Vision Transformer into voxel representations to enhance bimanual robotic manipulation. Specifically, we extract…
Generalizable Imitation Learning Through Pre-Trained Representations
Wei-Di Chang, Francois Hogan, Scott Fujimoto +2
In this paper, we leverage self-supervised vision transformer models and their emergent semantic abilities to improve the generalization abilities of imitation learning policies. W…
Tractable Representations for Convergent Approximation of Distributional HJB Equations
Julie Alhosh, Harley Wiltzer, David Meger
In reinforcement learning (RL), the long-term behavior of decision-making policies is evaluated based on their average returns. Distributional RL has emerged, presenting techniques…