基于深度强化学习的大口径轴孔装配策略

姜玉峰,陈东生

Assembly strategy for large-diameter peg-in-hole based on deep reinforcement learning

Yu-feng JIANG,Dong-sheng CHEN

图 6 DDPGFA算法和DDPG算法训练过程奖励曲线

Fig.6 Reward curves of training process of DDPGFA and DDPG algorithms