Jämför metoder

	Policy gradient-metoder	Q-learning
Ämnesområde	Maskininlärning	Maskininlärning
Familj	Machine learning	Machine learning
Ursprungsår	1992	1992
Upphovsperson	Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)	Christopher Watkins & Peter Dayan
Typ	Policy-based reinforcement learning	Model-free reinforcement-learning control algorithm
Ursprungskälla	Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256.	Watkins, C. J. C. H., & Dayan, P. (1992). Q-learning. Machine Learning, 8(3–4), 279–292.
Alias	REINFORCE, actor-critic, policy optimization, politika gradyanı	Q-learning algorithm, tabular Q-learning, off-policy TD control, Q-öğrenme
Närliggande	4	3
Sammanfattning	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.	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.