পদ্ধতির তুলনা করুন

	সীমাবদ্ধতা প্রোগ্রামিং	গভীর শক্তিশালীকরণ শিক্ষা
ক্ষেত্র	অনুকূলকরণ	গভীর শিখন
পরিবার	Process / pipeline	Machine learning
উদ্ভবের বছর	2006	2015
প্রবর্তক	Rossi, van Beek & Walsh	Mnih, V. et al. (DQN)
ধরন	Declarative combinatorial optimization	Sequential decision-making (agent–environment interaction)
মৌলিক উৎস	Rossi, F., van Beek, P., & Walsh, T. (Eds.). (2006). Handbook of Constraint Programming. Elsevier. ISBN: 978-0-444-52726-4	Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533.
অপর নাম	Constraint Satisfaction Programming, Constraint-Based Optimization, Kısıt Programlama, CSP Optimization	Derin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL
সম্পর্কিত	3	4
সারসংক্ষেপ	Constraint Programming (CP) is a declarative optimization paradigm in which a problem is formulated as a set of variables, finite domains, and constraints, and a solver systematically searches for assignments that satisfy all constraints. Formalized comprehensively by Rossi, van Beek, and Walsh in their 2006 Handbook of Constraint Programming, CP unifies propagation-based pruning with intelligent backtracking search to tackle combinatorial problems across scheduling, planning, and configuration domains.	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.