… an efficient algorithm to solve the complicated multiple intersections control problems whose state-action spaces are vast. To solve this problem, we propose a DeepReinforcement …
… Deepreinforcement learning (DRL) has gained great success by learning directly from high-… DRL and propose a framework of Symbolic DeepReinforcement Learning (SDRL) that can …
Z Huang, J Wu, C Lv - IEEE Transactions on Neural Networks …, 2022 - ieeexplore.ieee.org
… The superior sample efficiency of our proposed method is … , “Reinforced imitation: Sample efficientdeepreinforcement … policy maximum entropy deepreinforcement learning with a …
… Our goal is to improve the sample efficiency of deepreinforcement learning by making a simple yet effective modification. Without a single change of the network structure, training …
… Burgard, “Deepreinforcement learning with successor features … in indoor scenes using deep reinforcement learning,” in IEEE … aware motion planning with deepreinforcement learning,” …
V Mai, K Mani, L Paull - arXiv preprint arXiv:2201.01666, 2022 - arxiv.org
… In this work, we present a method to enhance the sample efficiency of deepreinforcement learning algorithms. As such, it is agnostic to the applications, and per se does not raise any …
… , etc. on the learning dynamics of deep RL algorithms, using tools from deep learning theory, is likely to be key towards developing robust and data-efficientdeep RL algorithms. …
… deepreinforcement learning approaches to solve this problem. Particular attention is given to actor-critic methods, off-policy reinforcement … of the art in deep learning approaches for …
… The focus of this work is sample-efficientdeepreinforcement learning (… Our work can be seen as an efficient approximate … Survey of deepreinforcement learning for motion planning of …