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.
Izvorni zapis
Citati kopirani doslovno iz izvornog zapisa metode. Ne impliciraju nikakvu provjeru na razini tvrdnje.
- 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
Uređene tvrdnje
Tvrdnje pohranjene u knjigu dokaza, svaka s vlastitom procjenom.
Ovaj prikaz ne izmišlja procjenu tvrdnje kada knjiga dokaza nema nijednu.
Povezane metode
Generirano iz grafa metode i prikazano kao strojno predložene relacije — ne implicira se nikakva tvrdnja dokaza.