all AI news
MBDP: A Model-based Approach to Achieve both Robustness and Sample Efficiency via Double Dropout Planning
May 3, 2024, 4:54 a.m. | Wanpeng Zhang, Xi Xiao, Yao Yao, Mingzhe Chen, Dijun Luo
cs.LG updates on arXiv.org arxiv.org
Abstract: Model-based reinforcement learning is a widely accepted solution for solving excessive sample demands. However, the predictions of the dynamics models are often not accurate enough, and the resulting bias may incur catastrophic decisions due to insufficient robustness. Therefore, it is highly desired to investigate how to improve the robustness of model-based RL algorithms while maintaining high sampling efficiency. In this paper, we propose Model-Based Double-dropout Planning (MBDP) to balance robustness and efficiency. MBDP consists of …
abstract arxiv bias cs.lg decisions dropout dynamics efficiency however planning predictions reinforcement reinforcement learning robustness sample solution type via
More from arxiv.org / cs.LG updates on arXiv.org
Efficient Data-Driven MPC for Demand Response of Commercial Buildings
2 days, 17 hours ago |
arxiv.org
Testing the Segment Anything Model on radiology data
2 days, 17 hours ago |
arxiv.org
Calorimeter shower superresolution
2 days, 17 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US