NAIV
NAIV
Neon AIVolution
Neon AIVolution (NAIV) is our research lab for building methods, systems, and
open-source tools for trustworthy AI. We are committed to advancing theory and practice of AI.
Paper Code
ShadOPE
ShadOPE Handles Absent-reward Data in Off-Policy Evaluation for MNAR MDPs.
TOPPOTOPPO Optimizes Proximal Policy Optimization for multi-task reinforcement learning with critic balancing.