Episodic Memory-Double Actor-Critic Twin Delayed Deep Deterministic Policy Gradient

Published: 01 Jan 2025, Last Modified: 17 Jul 2025Neural Networks 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•We propose an Episodic Memory-Double Actor–Critic (EMDAC) framework.•We design a Kalman filter optimizer-based episodic memory.•We design an intrinsic reward based on episodic memory.•We propose an EMDAC-TD3 algorithm.•Our method outperforms the SOTA methods on the popular benchmarks.
Loading