Jae-Kyung Cho Robotics and deep learning engineer

Archive

This is a personal space where I review papers and organize related documents.
이 곳은 개인적으로 논문을 리뷰하고 관련 문헌들을 정리하는 공간입니다.

전체 목록


22 Nov 2022 » Diary - Gym 0.26.0 update (truncted, no seed)

15 Nov 2022 » Diary - Dockerfile 한국어 설정

24 Oct 2022 » MLOps study - Raviraja Week 5: Docker

22 Oct 2022 » MLOps study - Raviraja Week 4: ONNX

17 Oct 2022 » MLOps study - Raviraja Week 3: DVC

13 Oct 2022 » MLOps study - Raviraja Week 2: Hydra

13 Oct 2022 » MLOps study - Raviraja Week 1: W&B

11 Oct 2022 » MLOps study - Raviraja Week 0: Pytorch Lightning

16 Aug 2022 » Diary - Sqaushed Gaussian policy for SAC

17 Jul 2022 » Diary - Network architecture for RL

25 Apr 2022 » Diary - Curious about GPU memory

09 Apr 2022 » Diary - Catastropic performance drop of off-policy RL methods

19 Mar 2022 » Diary - Frequent mistake for using torch.distributions.Normal

06 Mar 2022 » Paper review - Diff-DAC: Distributed Actor-Critic for Average Multitask Deep Reinforcement Learning

11 Feb 2022 » Diary - How to solve discrete-SAC loss explosion problem?

30 Jan 2022 » Paper review - Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback

29 Jan 2022 » Diary - How to use proper tense for writing academic paper?

23 Jan 2022 » Paper review - Interactive teaching strategies for agent training

17 Jan 2022 » Paper review - Learning latent representations to influence multi-agent interaction

10 Jan 2022 » Paper review - Learning trajectory preferences for manipulators via iterative improvement

01 Jan 2022 » Paper review - A survey of preference-based reinforcement learning methods