Jun 28, 2022 · In this paper, we propose the Quasi-Median Operation, a novel way to mitigate the underestimation bias by selecting the quasi-median from ...

In this paper, we propose the Quasi-Median. Operation, a novel way to mitigate the underestimation bias by selecting the quasi-median from multiple state-action ...

Theoretically, the underestimation bias of the method is improved while the estimation variance is significantly reduced compared to Maxmin Q-learning, ...

Based on the quasi-median operation, we propose Quasi-Median Q-learning (QMQ) for the discrete action tasks and Quasi-Median Delayed Deep Deterministic Policy ...

Controlling underestimation bias in reinforcement learning via quasi-median operation. W Wei, Y Zhang, J Liang, L Li, Y Li. Proceedings of the AAAI Conference ...

May 23, 2024 · Controlling Underestimation Bias in Reinforcement Learning via Quasi-median Operation ... underestimation bias by selecting the quasi-median from ...

Controlling Underestimation Bias in Reinforcement Learning via Quasi-Median Operation. Wei Wei, Yujia Zhang, Jiye Liang, Lin Li, Yuze Li. [AAAI-22] Main Track.

Double Q-learning is a classical method for reducing overestimation bias, which is caused by taking maximum estimated values in the Bellman operation.

Oct 17, 2023 · Controlling underestimation bias in reinforcement learning via quasi-median operation. Proceedings of the AAAI Conference on Artificial ...