밤에 쓰는 편지 밤에 쓰는 편지

* Google Researchhttps://research.google/blog/?search=reinforcement& Latest News from Google Research Blog - Google Research research.google * Open AI Spinning up https://spinningup.openai.com/en/latest/ Welcome to Spinning Up in Deep RL! — Spinning Up documentation© Copyright 2018, OpenAI. Revision 038665d6.spinningup.openai.com * Policy Gradient Algorithmshttps://lilianweng.github.io/posts/20..

https://www.youtube.com/playlist?list=PLzvYlJMoZ02Dxtwe-MmH4nOB5jYlMGBjr Reinforcement Learning By the Book www.youtube.com https://www.youtube.com/playlist?list=PLwRJQ4m4UJjNymuBM9RdmB3Z9N5-0IlY0 Foundations of Deep RL -- 6-lecture series by Pieter Abbeel www.youtube.com * DeepMind 와 Pieter Abbeel 교수님의 lecture 강추. RL을 공부한다면 필수 시청 * Mutual Information youtube series는 simulation을 시각적으로 정말 잘 보여줌...

https://openreview.net/pdf?id=qqnttX9LPo↑ Typo... equation (2) Action-value 수식 Q(s,a) 에서 summation에 transition probability 누락됨!!(이 오타를 Bellman님이 싫어합니다)

* f-divergence* f-divergence examples (KL-divergence, Total Variation Distance)* Aligning LMs with Preferences through f-divergence Minimization* Algorithm

https://arxiv.org/pdf/2302.08215(Jun 2023 ICML 2023) 짜잔~ 종합선물세트 입니다~!f-divergence로 대동단결.옛다. 크리스마스 선물 받아랏~! 너무 당연한 이야기이지만, 목표를 어떻게 설정하느냐에 따라 인생은 완전히 달라진다.목적지 변경은 우리를 완전히 다른 방향으로 이끌기도 한다.objective function (loss function)에 따라서 model의 behavior가 달라지는 건 참 흥미진진하다.(좀 더 구체적으로는..- 어떠한 measure로 target distribution을 approximate할 것인가- metric에 따라 convergence하는 양상은 어떻게 달라지는가) 이 논문을 읽는데 왜케 행복하지? ㅜㅜ 이 논문을 읽기 위해..

https://arxiv.org/pdf/2112.00791(Jun 2022 ICML 2022)AbstractMachine learning is shifting towards general-purpose pretrained generative models, trained in a self-supervised manner on large amounts of data, which can then be applied to solve a large number of tasks. However, due to their generic training methodology, these models often fail to meet some of the downstream requirements (e.g., halluc..

1. Example of Parallel Line Density2. Wasserstein Distance with GAN3. Kantarovich-Rubinstein Duality4. Wasserstein as Primal LP5. Wasserstein as Dual LP6. Property of Dual LP on Wasserstein Distance7. Lipschitz Continuity8. Dual Problem of Wasserstein Distance9. Kantorovich-Rubinstein Duality & Wasserstein GAN