Võrdle meetodeid
Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.
| Nõrgalt juhendatud tugevdamisõpe× | Tugevdamisõpe× | |
|---|---|---|
| Valdkond | Süvaõpe | Süvaõpe |
| Perekond | Machine learning | Machine learning |
| Tekkeaasta≠ | 2010s–present | 1950s–1998 |
| Looja≠ | Multiple contributors; reward-learning framing: Christiano et al. (2017) | Sutton, R. S. & Barto, A. G. (formalised); Bellman, R. (foundations) |
| Tüüp≠ | Reinforcement learning with imperfect or partial reward supervision | Sequential decision-making framework |
| Algallikas | Sutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6 | Sutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6 |
| Rööpnimetused | WSRL, weak-reward RL, imperfect-reward reinforcement learning, reward-impoverished RL | RL, reward-based learning, trial-and-error learning, policy optimization |
| Seotud≠ | 3 | 2 |
| Kokkuvõte≠ | Weakly supervised reinforcement learning (WSRL) trains agents in environments where the reward signal is imperfect, sparse, delayed, or only partially informative — unlike dense fully-supervised RL. The agent must learn effective policies despite incomplete feedback, using auxiliary signals, reward modeling, or preference learning to compensate for the weak supervision. | 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. |
| ScholarGateAndmestik ↗ |
|
|