Pinned Repositories
Reinforcement-Learning-Comparative-Study
Comparative study of Reinforcement Learning Algorithms on Ping Pong game: In the current design of experience replay we sample uniformly to obtain the minibatch and update the model. Devising a way to sample more experience points close to the tricky areas would help solving this problem, better the training rate and improve convergence. We designed a game environment for the Android platform as few such environments are available at the moment. Moreover, during the pre-processing game we removed the background and score to reduce clutter and increase likeliness of successful training. It would be interesting to see how restoring the background affects agent’s performance. Overall, our results show the capacity of Deep neural networks and how a generic reinforcement learning setup such as this could learn and play the game with very minimal domain knowledge.
DSHS_2-9_Schedule
대전대신고등학교 2학년 9반 시간표 알림입니다. Whale Extension에 최적화되어있습니다.
kdh-yu
Ping_Pong_AI
AI playing against each other, using deep reinforcement learning (CNN and Q-Learning)
AI_ERC
awesome-public-datasets
A topic-centric list of HQ open datasets.
BDIP
Biomedical Image Processing by Prof. Jongmin Lee
csd_assignment_1
DiffuMask
[ICCV2023] DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
group11_dsp
Data Science Project - Group 11
kdh-yu's Repositories
kdh-yu/ML1-Project
Machine learning 1 group 9, Lung cancer prediction.
kdh-yu/AI_ERC
kdh-yu/kdh-yu.github.io
kdh-yu/kdh-yu
kdh-yu/ML2
kdh-yu/BDIP
Biomedical Image Processing by Prof. Jongmin Lee
kdh-yu/pan_tompkins
생체신호및시스템 실습 - Pan-Tompkins algorithm
kdh-yu/DiffuMask
[ICCV2023] DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
kdh-yu/OOP_Java
Object Oriented System Design by Heejin Park, Dept. of Data Science
kdh-yu/group11_dsp
Data Science Project - Group 11
kdh-yu/csd_assignment_1
kdh-yu/awesome-public-datasets
A topic-centric list of HQ open datasets.
kdh-yu/recommender_system_with_Python
recommender system tutorial with Python
kdh-yu/wookyoungkim
kdh-yu/HiDT
Official repository for the paper High-Resolution Daytime Translation Without Domain Labels (CVPR2020, Oral)
kdh-yu/DSHS_2-9_Schedule
대전대신고등학교 2학년 9반 시간표 알림입니다. Whale Extension에 최적화되어있습니다.
kdh-yu/Reinforcement-Learning-Comparative-Study
Comparative study of Reinforcement Learning Algorithms on Ping Pong game: In the current design of experience replay we sample uniformly to obtain the minibatch and update the model. Devising a way to sample more experience points close to the tricky areas would help solving this problem, better the training rate and improve convergence. We designed a game environment for the Android platform as few such environments are available at the moment. Moreover, during the pre-processing game we removed the background and score to reduce clutter and increase likeliness of successful training. It would be interesting to see how restoring the background affects agent’s performance. Overall, our results show the capacity of Deep neural networks and how a generic reinforcement learning setup such as this could learn and play the game with very minimal domain knowledge.
kdh-yu/Ping_Pong_AI
AI playing against each other, using deep reinforcement learning (CNN and Q-Learning)