Self-supervised Reinforcement Learning
Self-supervised Reinforcement Learning (SSL-RL) augments standard RL training with self-supervised auxiliary objectives — such as contrastive, predictive, or data-augmentation-based tasks — applied to the agent's own experience. These objectives improve the quality of learned representations without requiring extra human labels, enabling faster convergence and better sample efficiency, especially in high-dimensional observation spaces like raw pixels.
Kilderegister
Siteringer kopiert ordrett fra metodens kilderegister. Ingen påstandsnivåverifisering er underforstått fra dem.
- Laskin, M., Srinivas, A., & Abbeel, P. (2020). CURL: Contrastive Unsupervised Representations for Reinforcement Learning. Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 5639–5650. · URL
- Laskin, M., Lee, K., Stooke, A., Pinto, L., Abbeel, P., & Srinivas, A. (2021). Reinforcement Learning with Augmented Data. Advances in Neural Information Processing Systems (NeurIPS), 33, 19884–19895. · URL
Kuraterte påstander
Påstander lagret i bevishovedboken, hver med sin egen vurdering.
Denne visningen finner ikke opp en påstandsvurdering når hovedboken ikke har noen.
Relaterte metoder
Generert fra metodegrafen og vist som maskinforslåtte relasjoner – ingen bevispåstand er underforstått.