手法を比較

	Semi-supervised Reinforcement Learning	弱教師あり強化学習
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2020s	2010s–present
提唱者	Multiple contributors (Laskin, Srinivas, Abbeel et al.)	Multiple contributors; reward-learning framing: Christiano et al. (2017)
種類	Semi-supervised training paradigm for RL agents	Reinforcement learning with imperfect or partial reward supervision
原典	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.	Sutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6
別名	SSRL, semi-supervised RL, RL with unlabeled data, label-efficient reinforcement learning	WSRL, weak-reward RL, imperfect-reward reinforcement learning, reward-impoverished RL
関連	6	3
概要	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.	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.