This paper presents an innovative method for humanoid robots to acquire a comprehensive set of motor skills through reinforcement learning. The approach utilizes an achievement-triggered multi-path reward function rooted in developmental robotics principles, facilitating the robot to learn gross motor skills typically mastered by human infants within a single training phase. The proposed method outperforms standard reinforcement learning techniques in success rates and learning speed within a simulation environment. By leveraging the principles of self-discovery and exploration integral to infant learning, this method holds the potential to significantly advance humanoid robot motor skill acquisition.

翻译：本文提出了一种创新方法，使人形机器人能够通过强化学习获得一套全面的运动技能。该方法利用基于发展机器人学原理的成就触发多路径奖励函数，使机器人能够在单一训练阶段内学习人类婴儿通常掌握的大肌肉运动技能。在仿真环境中，所提方法在成功率和学习速度上均优于标准强化学习技术。通过借鉴婴儿学习中自我发现与探索的核心原则，该方法有望显著推动人形机器人运动技能的习得。