Abstract The Digital Transformation Services Internship Program at PT Arkatama Multi
Solusindo aims to provide opportunities for intern students to develop themselves through …

Despite some successful applications of goal-driven navigation, existing deep reinforcement
learning (DRL)-based approaches notoriously suffers from poor data efficiency issue. One of …

This paper provides a comprehensive review of the current status, advancements, and future
prospects of humanoid robots, highlighting their significance in driving the evolution of next …

Studying the representational capacity of neural networks to learn nonlinear rewards is
necessary in a complex and nonlinear environment. Over recent years, the maximum …

The recent paramount success of the gig economy has introduced new business
opportunities in different areas such as food delivery service. However, there are food …

深度确定性策略梯度(deep deterministic policy gradient, DDPG) 算法在自动驾驶领域中应用
广泛, 但DDPG 算法因采用均匀采样而导致低效率策略比例较高, 训练效率低, 收敛速度慢等 …

随着深度强化学习的研究与发展, 强化学习在博弈与优化决策, 智能驾驶等现实问题中的应用也
取得显著进展. 然而强化学习在智能体与环境的交互中存在人工设计奖励函数难的问题 …

Offline reinforcement learning aims to learn effective policies from a fixed set of data
collected in advance and without further interaction with the environment during learning …

We live in the era of big data in which the advancement of sensor and monitoring
technologies, data storage and management, and computer processing power enable us to …