Description
A Stochastic Dueling Network, or SDN, is an architecture for learning a value function . The SDN learns both and off-policy while maintaining consistency between the two estimates. At each time step it outputs a stochastic estimate of and a deterministic estimate of .
Papers Using This Method
Dynamics of Resource Allocation in O-RANs: An In-depth Exploration of On-Policy and Off-Policy Deep Reinforcement Learning for Real-Time Applications2024-11-17Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues2024-04-12Distributional Estimation of Data Uncertainty for Surveillance Face Anti-spoofing2023-09-18PDVN: A Patch-based Dual-view Network for Face Liveness Detection using Light Field Focal Stack2023-01-17Asynchronous Curriculum Experience Replay: A Deep Reinforcement Learning Approach for UAV Autonomous Motion Control in Unknown Dynamic Environments2022-07-04Is Word Error Rate a good evaluation metric for Speech Recognition in Indic Languages?2022-03-30Learning Reward Machines: A Study in Partially Observable Reinforcement Learning2021-12-17A-DeepPixBis: Attentional Angular Margin for Face Anti-Spoofing2021-03-01Learning Reward Machines for Partially Observable Reinforcement Learning2019-12-01Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces2018-02-11Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations2018-01-31Sample Efficient Actor-Critic with Experience Replay2016-11-03