Rekod bukti kaedah

Deep Reinforcement Learning

Deep Reinforcement Learning combines neural networks with reinforcement learning so an agent learns by interacting with an environment, popularised by Mnih and colleagues' 2015 Nature work on human-level Atari control. Instead of learning from a fixed labelled dataset, the agent takes actions, observes rewards, and gradually shapes a policy that maximises long-run return.

Sources recorded, not reviewed

Rekod sumber

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

Deep Reinforcement Learning (DQN / PPO / A3C)

Rekod kaedah taksonomik · ml-model / deep-learning

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.

Same method familyNeural Architecture Searchmachine-suggested · Relational suggestion, not evidence.Same method familyRandom Forestmachine-suggested · Relational suggestion, not evidence.Same method familyRecurrent Neural Networkmachine-suggested · Relational suggestion, not evidence.Same method familyXGBoostmachine-suggested · Relational suggestion, not evidence.