19 citations · 109 across the 21 of their papers we have counts for
3 papers · 1 filter
Sample-based Uncertainty Quantification with a Single Deterministic Neural Network
Takuya Kanazawa, Chetan Gupta
Development of an accurate, flexible, and numerically efficient uncertainty quantification (UQ) method is one of fundamental challenges in machine learning. Previously, a UQ method…
Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control
Takuya Kanazawa, Haiyan Wang, Chetan Gupta
Uncertainty quantification is one of the central challenges for machine learning in real-world applications. In reinforcement learning, an agent confronts two kinds of uncertainty,…
K-nearest Multi-agent Deep Reinforcement Learning for Collaborative Tasks with a Variable Number of Agents
Hamed Khorasgani, Haiyan Wang, Hsiu-Khuern Tang +1
Traditionally, the performance of multi-agent deep reinforcement learning algorithms are demonstrated and validated in gaming environments where we often have a fixed number of age…