Work

Improved Techniques for Offline Reinforcement Learning: Advantage Value Estimation and Layernorm

Year: 2025

Type: conference-paper

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp49660.2025.10890751

Authors: Xiaosong Liu, Quan Liu, Lan Wu

Institution: Soochow University

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

Funder: National Natural Science Foundation of China

OpenAlex ID: W4408355010

FWCI: 1.977

Cites: 19

Cited by: 2

Related to: 10