.png){kind=icon}
返回
Enhanced Deep Deterministic Policy Gradient Algorithm Using Grey Wolf Optimizer for Continuous Control Tasks
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3341507.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep Reinforcement Learning (DRL) allows agents to make decisions in a specific environment based on a reward function, without prior knowledge. Adapting hyperparameters significantly impacts the learning process and time. Precise estimation of hyperparameters during DRL training poses a major challenge. To tackle this problem, this study utilizes Grey Wolf Optimization (GWO), a metaheuristic algorithm, to optimize the hyperparameters of the Deep Deterministic Policy Gradient (DDPG) algorithm for achieving optimal control strategy in two simulated Gymnasium environments provided by OpenAI. The ability to adapt hyperparameters accurately contributes to faster convergence and enhanced learning, ultimately leading to more efficient control strategies. The proposed DDPG-GWO algorithm is evaluated in the 2DRobot and MountainCarContinuous simulation environments, chosen for their ease of implementation. Our experimental results reveal that optimizing the hyperparameters of the DDPG using the GWO algorithm in the Gymnasium environments maximizes the total rewards during testing episodes while ensuring the stability of the learning policy. This is evident in comparing our proposed DDPG-GWO agent with optimized hyperparameters and the original DDPG. In the 2DRobot environment, the original DDPG had rewards ranging from -150 to -50, whereas, in the proposed DDPG-GWO, they ranged from -100 to 100 with a running average between 1 and 800 across 892 episodes. In the MountainCarContinuous environment, the original DDPG struggled with negative rewards, while the proposed DDPG-GWO achieved rewards between 20 and 80 over 218 episodes with a total of 490 timesteps.
Keyword:
Deep deterministic policy gradient
deep reinforcement learning
grey wolf optimization
hyperparameters optimization
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
分享收藏Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
PREAI
分享收藏Effects of air constituents on thermosensitivities of preoptic neurons: hypoxia versus hypercapnia
PREAI
分享收藏The Influence of Dominance and Sociolinguistic Context on Bilingual Preschoolers' Language Choice
PREAI
分享收藏Conglomerates record the tectonic evolution of the Yarlung-Tsangpo suture zone in southern Tibet
PREAI
分享收藏48MO Characteristics and outcomes of 76 patients with pleomorphic liposarcoma: The Gustave Roussy experience48MO 76例多形性脂肪肉瘤患者的特征与结局：居斯塔夫·鲁西研究所的经验.png)
ESMO Open
OAAI
ESMO OpenIF0
OAAI分享收藏
查看更多内容