방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 약한 지도 강화학습× | 준지도 강화학습× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2010s–present | 2020s |
| 창시자≠ | Multiple contributors; reward-learning framing: Christiano et al. (2017) | Multiple contributors (Laskin, Srinivas, Abbeel et al.) |
| 유형≠ | Reinforcement learning with imperfect or partial reward supervision | Semi-supervised training paradigm for RL agents |
| 원전≠ | 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 ↗ |
| 별칭 | WSRL, weak-reward RL, imperfect-reward reinforcement learning, reward-impoverished RL | SSRL, semi-supervised RL, RL with unlabeled data, label-efficient reinforcement learning |
| 관련≠ | 3 | 6 |
| 요약≠ | 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. |
| ScholarGate데이터셋 ↗ |
|
|