all AI news
When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning
March 1, 2024, 5:44 a.m. | Siliang Zeng, Chenliang Li, Alfredo Garcia, Mingyi Hong
cs.LG updates on arXiv.org arxiv.org
Abstract: Offline inverse reinforcement learning (Offline IRL) aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving. However, the structure of an expert's preferences implicit in observed actions is closely linked to the expert's model of the environment dynamics (i.e. …
abstract agent arxiv cs.ai cs.lg dynamics environment expert expertise framework generative likelihood offline reinforcement reinforcement learning set type world world models
More from arxiv.org / cs.LG updates on arXiv.org
Efficient Data-Driven MPC for Demand Response of Commercial Buildings
2 days, 20 hours ago |
arxiv.org
Testing the Segment Anything Model on radiology data
2 days, 20 hours ago |
arxiv.org
Calorimeter shower superresolution
2 days, 20 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