RL-background

The elements of reinforcement learning, Q-learning

λ³Έ ν¬μŠ€νŒ…μ€ κ°•ν™”ν•™μŠ΅μ„ 이해함에 μžˆμ–΄ ν•„μˆ˜μ μΈ λ‚΄μš©μ„ κ°„λ‹¨νžˆ μ •λ¦¬ν•˜κ³ μž μž‘μ„±ν•˜μ˜€μŠ΅λ‹ˆλ‹€.

  • κ΄€λ ¨ λ„μ„œ: νŒ¨ν‚€μ§€ 없이 R둜 κ΅¬ν˜„ν•˜λŠ” 심측 κ°•ν™”ν•™μŠ΅ [yes24] [ꡐ보문고]

Previous[CVPR 2019] Class-Balanced Loss Based on Effective Number of SamplesNextIntroduction

Last updated

Was this helpful?