ScholarGate
Асистент

Сравнение на методи

Прегледайте избраните методи един до друг; редовете с разлики са откроени.

Q-обучение×Дълбоко обучение с подкрепление×Динамично оптимиране×
ОбластМашинно обучениеДълбоко обучениеОптимизация
СемействоMachine learningMachine learningProcess / pipeline
Година на възникване199220151957
СъздателChristopher Watkins & Peter DayanMnih, V. et al. (DQN)Richard Bellman
ТипModel-free reinforcement-learning control algorithmSequential decision-making (agent–environment interaction)Exact combinatorial optimization via recursive decomposition
Основополагащ източникWatkins, C. J. C. H., & Dayan, P. (1992). Q-learning. Machine Learning, 8(3–4), 279–292. DOI ↗Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗Bellman, R. (1957). Dynamic Programming. Princeton University Press. ISBN: 978-0-691-07951-6
Други названияQ-learning algorithm, tabular Q-learning, off-policy TD control, Q-öğrenmeDerin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRLDP, Bellman's Principle of Optimality, Recursive Optimization, Dinamik Programlama
Свързани343
РезюмеQ-learning, introduced by Christopher Watkins and Peter Dayan in 1992, is a model-free reinforcement-learning algorithm that learns the value of taking each action in each state — the Q-function — purely from experience, without a model of the environment. It is off-policy: it learns the optimal action-values while following an exploratory behaviour policy, and under standard conditions it provably converges to the optimal policy.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.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.
ScholarGateНабор от данни
  1. v1
  2. 2 Източници
  3. PUBLISHED
  1. v1
  2. 2 Източници
  3. PUBLISHED
  1. v1
  2. 1 Източници
  3. PUBLISHED

Към търсенето Изтегляне на слайдове

ScholarGateСравнение на методи: Q-Learning · Deep Reinforcement Learning · Dynamic Programming. Извлечено на 2026-06-17 от https://scholargate.app/bg/compare