So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| Phương pháp độ dốc chính sách× | Học tăng cường sâu× | |
|---|---|---|
| Lĩnh vực≠ | Học máy | Học sâu |
| Họ | Machine learning | Machine learning |
| Năm ra đời≠ | 1992 | 2015 |
| Người khởi xướng≠ | Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem) | Mnih, V. et al. (DQN) |
| Loại≠ | Policy-based reinforcement learning | Sequential decision-making (agent–environment interaction) |
| Công trình gốc≠ | Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256. DOI ↗ | Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗ |
| Tên gọi khác≠ | REINFORCE, actor-critic, policy optimization, politika gradyanı | Derin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL |
| Liên quan | 4 | 4 |
| Tóm tắt≠ | Policy gradient methods are reinforcement-learning algorithms that optimize a parameterized policy directly by gradient ascent on the expected return, rather than learning action-values and acting greedily. Founded on Ronald Williams' 1992 REINFORCE algorithm and the policy gradient theorem of Sutton and colleagues (2000), they naturally handle stochastic and continuous action spaces and underpin modern actor-critic and deep-RL algorithms. | Deep Reinforcement Learning combines neural networks with reinforcement learning so an agent learns by interacting with an environment, popularised by Mnih and colleagues' 2015 Nature work on human-level Atari control. Instead of learning from a fixed labelled dataset, the agent takes actions, observes rewards, and gradually shapes a policy that maximises long-run return. |
| ScholarGateBộ dữ liệu ↗ |
|
|