Compara mètodes

	Aprenentatge per Reforç Profund	Programació Dinàmica	Mètodes de Gradient de Política
Camp	Aprenentatge profund	Optimització	Aprenentatge automàtic
Família	Machine learning	Process / pipeline	Machine learning
Any d'origen	2015	1957	1992
Autor original	Mnih, V. et al. (DQN)	Richard Bellman	Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)
Tipus	Sequential decision-making (agent–environment interaction)	Exact combinatorial optimization via recursive decomposition	Policy-based reinforcement learning
Font seminal	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.
Àlies	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
Relacionats	4	3	4
Resum	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.