手法を比較

	Q学習	深層強化学習	動的計画法	方策勾配法
分野	機械学習	深層学習	最適化	機械学習
系統	Machine learning	Machine learning	Process / pipeline	Machine learning
提唱年	1992	2015	1957	1992
提唱者	Christopher Watkins & Peter Dayan	Mnih, V. et al. (DQN)	Richard Bellman	Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)
種類	Model-free reinforcement-learning control algorithm	Sequential decision-making (agent–environment interaction)	Exact combinatorial optimization via recursive decomposition	Policy-based reinforcement learning
原典	Watkins, C. J. C. H., & Dayan, P. (1992). Q-learning. Machine Learning, 8(3–4), 279–292.	Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533.	Bellman, R. (1957). Dynamic Programming. Princeton University Press. ISBN: 978-0-691-07951-6	Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256.
別名	Q-learning algorithm, tabular Q-learning, off-policy TD control, Q-öğrenme	Derin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL	DP, Bellman's Principle of Optimality, Recursive Optimization, Dinamik Programlama	REINFORCE, actor-critic, policy optimization, politika gradyanı
関連	3	4	3	4
概要	Q-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.	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.