Rekod bukti kaedah

Weakly supervised reinforcement learning

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.

Sources recorded, not reviewed

Rekod sumber

Petikan disalin secara verbatim daripada rekod sumber kaedah. Tiada pengesahan peringkat tuntutan disimpulkan daripadanya.

Weakly Supervised Reinforcement Learning

Rekod kaedah taksonomik · ml-model / deep-learning

Sutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. · ISBN 978-0-262-03924-6
Christiano, P., Leike, J., Brown, T. B., Martic, M., Legg, S. & Amodei, D. (2017). Deep reinforcement learning from human preferences. Advances in Neural Information Processing Systems (NeurIPS), 30. · URL

Buka kaedah penuh

Tuntutan yang dikurasi

Tuntutan disimpan dalam lejar bukti, setiap satu dengan penilaiannya sendiri.

Tiada tuntutan terkurasi lagi

Pandangan ini tidak mencipta penilaian tuntutan apabila lejar tiada.

Kaedah berkaitan

Dijana daripada graf kaedah dan ditunjukkan sebagai perhubungan yang dicadangkan mesin — tiada tuntutan bukti disimpulkan.

Taxonomic bucketReinforcement Learningmachine-suggested · Relational suggestion, not evidence.Taxonomic bucketSelf-supervised Reinforcement Learningmachine-suggested · Relational suggestion, not evidence.Taxonomic bucketSemi-supervised Reinforcement Learningmachine-suggested · Relational suggestion, not evidence.