Võrdle meetodeid
Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.
| Tugevdamisõpe× | Poliitika gradiendi meetodid× | |
|---|---|---|
| Valdkond≠ | Süvaõpe | Masinõpe |
| Perekond | Machine learning | Machine learning |
| Tekkeaasta≠ | 1950s–1998 | 1992 |
| Looja≠ | Sutton, R. S. & Barto, A. G. (formalised); Bellman, R. (foundations) | Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem) |
| Tüüp≠ | Sequential decision-making framework | Policy-based reinforcement learning |
| Algallikas≠ | Sutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6 | Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256. DOI ↗ |
| Rööpnimetused | RL, reward-based learning, trial-and-error learning, policy optimization | REINFORCE, actor-critic, policy optimization, politika gradyanı |
| Seotud≠ | 2 | 4 |
| Kokkuvõte≠ | Reinforcement Learning (RL) is a framework in which an agent learns to make sequential decisions by interacting with an environment, receiving scalar reward signals, and updating a policy to maximise cumulative future reward. Unlike supervised learning, no labeled examples are provided; the agent discovers optimal behavior entirely through experience and delayed feedback. | 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. |
| ScholarGateAndmestik ↗ |
|
|