learning efficiency

Bilibili Tech

Dec 6, 2024 · Artificial Intelligence

Ensemble-based Offline-to-Online Reinforcement Learning (ENOTO): Methodology, Experiments, and Analysis

ENOTO introduces ensemble Q‑networks into the offline‑to‑online reinforcement‑learning pipeline, using minimum‑Q and uncertainty‑driven exploration to stabilize fine‑tuning, boost learning efficiency, and achieve 10‑25 % higher cumulative returns with minimal online interaction across MuJoCo and AntMaze benchmarks.

AntMazeENOTOEnsemble Q-Networks

0 likes · 16 min read

Ensemble-based Offline-to-Online Reinforcement Learning (ENOTO): Methodology, Experiments, and Analysis

Model Perspective

Oct 18, 2024 · Fundamentals

How to Model Daily Life with Functions: Nutrition, Social Media, and Study Efficiency

By treating everyday processes—dietary choices, social media activity, and study habits as mathematical functions, we can collect input data, build predictive models, and optimize outcomes, illustrating how function-based thinking turns complex real‑world problems into solvable equations.

function analysislearning efficiencymathematical modeling

0 likes · 7 min read