all AI news
Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policies
May 3, 2024, 4:53 a.m. | Finn Rietz, Erik Schaffernicht, Stefan Heinrich, Johannes A. Stork
cs.LG updates on arXiv.org arxiv.org
Abstract: Reinforcement learning policies are typically represented by black-box neural networks, which are non-interpretable and not well-suited for safety-critical domains. To address both of these issues, we propose constrained normalizing flow policies as interpretable and safe-by-construction policy models. We achieve safety for reinforcement learning problems with instantaneous safety constraints, for which we can exploit domain knowledge by analytically constructing a normalizing flow that ensures constraint satisfaction. The normalizing flow corresponds to an interpretable sequence of transformations …
abstract arxiv box construction cs.ai cs.lg domains flow networks neural networks policies policy reinforcement reinforcement learning safe safety safety-critical type
More from arxiv.org / cs.LG updates on arXiv.org
Testing the Segment Anything Model on radiology data
1 day, 6 hours ago |
arxiv.org
Calorimeter shower superresolution
1 day, 6 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