Policy Gradient
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.
Zdrojový záznam
Citácie skopírované doslovne zo zdrojového záznamu metódy. Nevyplýva z nich žiadne overenie na úrovni tvrdenia.
- Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256. · DOI 10.1007/BF00992696
- Sutton, R. S., McAllester, D., Singh, S., & Mansour, Y. (2000). Policy gradient methods for reinforcement learning with function approximation. Advances in Neural Information Processing Systems, 12, 1057–1063. · URL
Spracované tvrdenia
Tvrdenia uložené v registri dôkazov, každé s vlastným hodnotením.
Tento pohľad nevymýšľa hodnotenie tvrdenia, ak register žiadne nemá.
Súvisiace metódy
Vygenerované z grafu metód a zobrazené ako vzťahy navrhnuté strojom – nevyplýva z nich žiadne tvrdenie o dôkaze.