手法を比較
選択した手法を並べて確認できます。異なる行はハイライト表示されます。
| 動的計画法× | 深層強化学習× | |
|---|---|---|
| 分野≠ | 最適化 | 深層学習 |
| 系統≠ | Process / pipeline | Machine learning |
| 提唱年≠ | 1957 | 2015 |
| 提唱者≠ | Richard Bellman | Mnih, V. et al. (DQN) |
| 種類≠ | Exact combinatorial optimization via recursive decomposition | Sequential decision-making (agent–environment interaction) |
| 原典≠ | Bellman, R. (1957). Dynamic Programming. Princeton University Press. ISBN: 978-0-691-07951-6 | Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗ |
| 別名≠ | DP, Bellman's Principle of Optimality, Recursive Optimization, Dinamik Programlama | Derin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL |
| 関連≠ | 3 | 4 |
| 概要≠ | Dynamic Programming (DP) is an exact optimization technique introduced by Richard Bellman in 1957 for solving multi-stage decision problems. It decomposes a complex problem into simpler, overlapping subproblems, solves each subproblem once, and stores the results to avoid redundant computation. Grounded in the Principle of Optimality, DP guarantees globally optimal solutions whenever the problem exhibits overlapping subproblems and optimal substructure. | 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. |
| ScholarGateデータセット ↗ |
|
|