Exploiting Estimation Bias in Clipped Double Q-Learning for Continous Control Reinforcement Learning Tasks
Authors:
- Niccolò TurcatoNTNiccolò Turcato
- Alberto SinigagliaASAlberto Sinigaglia
- Alberto Dalla LiberaALAlberto Dalla Libera
- Ruggero CarliRCRuggero Carli
- Gian Antonio SustoGSGian Antonio Susto
- 11 December 2025
- journal article
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 59 (26) , 1-6
Abstract
No abstract availableAll Related Versions
This publication has 2 references indexed in Scilit:
- Realistic Actor-Critic: A framework for balance between value overestimation and underestimationFrontiers in Neurorobotics, 2023
- A Tour of Reinforcement Learning: The View from Continuous ControlAnnual Review of Control, Robotics, and Autonomous Systems, 2019