Võrdle meetodeid
Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.
| Nõrgalt juhendatud tugevdamisõpe× | Poolitud õppimisega tugevdamine× | |
|---|---|---|
| Valdkond | Süvaõpe | Süvaõpe |
| Perekond | Machine learning | Machine learning |
| Tekkeaasta≠ | 2010s–present | 2020s |
| Looja≠ | Multiple contributors; reward-learning framing: Christiano et al. (2017) | Multiple contributors (Laskin, Srinivas, Abbeel et al.) |
| Tüüp≠ | Reinforcement learning with imperfect or partial reward supervision | Semi-supervised training paradigm for RL agents |
| Algallikas≠ | Sutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6 | Zhan, X., Zhu, X., & Shi, H. (2022). Deepthermal: Combustion optimization for thermal power generating units using offline reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence, 36(4), 4680–4688. link ↗ |
| Rööpnimetused | WSRL, weak-reward RL, imperfect-reward reinforcement learning, reward-impoverished RL | SSRL, semi-supervised RL, RL with unlabeled data, label-efficient reinforcement learning |
| Seotud≠ | 3 | 6 |
| 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. | Semi-supervised reinforcement learning (SSRL) combines standard reinforcement learning — where an agent learns from sparse reward signals — with semi-supervised techniques that extract structure from unlabeled environment interactions. The goal is to improve sample efficiency and generalization when reward feedback is costly, delayed, or available only for a fraction of the agent's experience. |
| ScholarGateAndmestik ↗ |
|
|