还要定时给机器彻底扫除尘土。
本文提出了基于过程奖赏和优先扫除的强化学习算法作为多机器人系统的冲突消解策略。
A reinforcement learning algorithm based on process reward and prioritized sweeping is presented as interference solving strategy.
本文提出了基于过程奖赏和优先扫除的强化学习算法作为多机器人系统的冲突消解策略。
A reinforcement learning algorithm based on process reward and prioritized sweeping is presented as interference solving strategy.
应用推荐