-
(2/3) GAN, F-Divergence, IPMRL/RL 2024. 12. 21. 17:00
1. Generalizing Loss of Divergence
2. Convex Conjugate Function
3. F-Divergence
4. Derivation of Optimal τ of Fenchel Conjugate
5. Difference of Two Probability Distributions
6. Integral Probability Metric
7. GAN + MMD
'RL > RL' 카테고리의 다른 글
[cdpg] Controlling Conditional Language Models without Catastrophic Forgetting (0) 2024.12.22 (3/3) GAN, F-Divergence, IPM (0) 2024.12.22 (1/3) GAN, F-Divergence, IPM (0) 2024.12.20 High Variance in Policy gradients (0) 2024.12.19 DPG (0) 2024.12.17