Machine learning
深度强化学习
深度强化学习将神经网络与强化学习相结合，使智能体通过与环境交互来学习。其流行得益于 Mnih 及其同事 2015 年在《自然》杂志上发表的关于人类水平 Atari 游戏控制的开创性工作。智能体并非从固定的标记数据集中学习，而是采取行动、观察奖励，并逐步形成一个能够最大化长期回报的策略。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI: 10.1038/nature14236 ↗
- Schulman, J. et al. (2017). Proximal Policy Optimization Algorithms. arXiv:1707.06347. link ↗
如何引用本页
ScholarGate. (2026, June 1). Deep Reinforcement Learning (DQN / PPO / A3C). ScholarGate. https://scholargate.app/zh/deep-learning/deep-reinforcement-learning
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →