HG2P: Hippocampus-inspired high-reward graph and model-free Q-gradient penalty for path planning and motion control
- 2 July 2025
- journal article
- Published by Elsevier in Neural Networks
- Vol. 191, 107781
Abstract
No abstract availableKeywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Cooperative motion planning and control for aerial-ground autonomous systems: Methods and applicationsProgress in Aerospace Sciences, 2024
- Lipschitzness is all you need to tame off-policy generative adversarial imitation learningMachine Learning, 2022
- Single-trial dynamics of hippocampal spatial representations are modulated by reward valueCurrent Biology, 2021
- Neural correlates underlying the effect of reward value on recognition memoryNeuroImage, 2019
- Post-learning Hippocampal Replay Selectively Reinforces Spatial Memory for Highly Rewarded LocationsCurrent Biology, 2019
- Reverse Replay of Hippocampal Place Cells Is Uniquely Modulated by Changing RewardNeuron, 2016
- The Cognitive Architecture of Spatial Navigation: Hippocampal and Striatal ContributionsNeuron, 2015
- Policy gradient in Lipschitz Markov Decision ProcessesMachine Learning, 2015
- Rewarded Outcomes Enhance Reactivation of Experience in the HippocampusNeuron, 2009
- Maze-solving by an amoeboid organismNature, 2000