Dohyun Kwon (@hilariouss)
github

hilariouss

Twitter logo Share LinkedIn logo Share Facebook logo Share

Top repositories

1

LSTM_VST_PVGF

Multi-scale LSTM based hourly Photovoltaic (PV) power generation forecasting
Python
34
star
2

-RL-PolicyGradient_summarization

이 μ €μž₯μ†ŒλŠ” κ°•ν™”ν•™μŠ΅μ˜ ν•™μŠ΅ 방법 쀑 ν•˜λ‚˜μΈ μ •μ±… 경사(policy gradient)에 λŒ€ν•œ 방법둠을 μ •λ¦¬ν•©λ‹ˆλ‹€.
Python
7
star
3

-RL-My_IEEE_Journal_Imple.-DDPG-

This repository contains my work submitted to IEEE Transactions on Vehicular Technology (TVT). The journal is about 'proactive caching policy learning in mmWave vehicular networks' with DDPG. Some part of the contents will be uploaded after submission.
3
star
4

-RL-Q_learning-Neural-network-

Q-learning with neural network
Python
2
star
5

LSTM_MNIST

Long term short memory with MNIST
Python
1
star
6

assignment06

assignment06
Jupyter Notebook
1
star
7

-RL-Context_Bandit

Context bandit problem with reinforcement learning
Python
1
star
8

Reinforcement_learning

Journey of RL implementations
1
star
9

assignment07

1
star
10

assignment01

CAU_Datamining assignment01
TeX
1
star
11

-RL-Double_Dueling_DQN

This repository implements the 'double dueling DQN', which extends the DQN.
Python
1
star
12

-TVT-A3C-Base

A3C base code (w/. Tensorflow) for TVT
Python
1
star
13

LSTM-examples

Examples of model w.r.t. LSTM
Python
1
star
14

-RL-DeepQNetwork_Cartpole

이 μ €μž₯μ†ŒλŠ” OpenAI gym의 cartpole ν™˜κ²½μ„ Deep Q Networkλ₯Ό ν™œμš©ν•΄ ν•™μŠ΅ν•˜λŠ” μ½”λ“œλ₯Ό λ‹΄κ³ μžˆμŠ΅λ‹ˆλ‹€.
Python
1
star
15

assignment03

Datamining class assignment03
Jupyter Notebook
1
star
16

-Multiarmed_bandit-Reinforcement-learning

This repository is implementation regarding "Multiarmed bandit problem"
Python
1
star
17

-RL-Q_learning

This repo. is about the Q-learning
Python
1
star
18

-TVT-DQN-Base

DQN base code (w/. Keras) for TVT
Python
1
star
19

assignment02

Datamining class assignment02
Jupyter Notebook
1
star
20

-RL-ReviewPapers

This is a repository for reviewing some interesting RL papers.
1
star
21

RL_MarkovDecisionProcess

This repository elaborates the implementation of the (finite) Markov decision process (MDP)
Python
1
star
22

-Reference-NLP_RL

Bag of references for paper work
1
star
23

assignment05

assignment05
Jupyter Notebook
1
star
24

-RL-AWS_DeepRacer_Project

λ³Έ μ €μž₯μ†ŒλŠ” μ•„λ§ˆμ‘΄ μ›Ή μ„œλΉ„μŠ€ (AWS)μ—μ„œ μΆœμ‹œν•œ 'κ°•ν™”ν•™μŠ΅ 기반 μžμœ¨μ£Όν–‰μžλ™μ°¨'인 AWS DeepRacerλ₯Ό ν™œμš©ν•œ 연ꡬ물듀을 μ €μž₯ν•©λ‹ˆλ‹€. AWS SageMaker 및 AWS RoboMakerλ₯Ό ν™œμš©ν•œ AWS DeepRacer ν”„λ‘œμ νŠΈ κ΄€λ ¨λœ νŒŒμΌλ“€μ΄ μ—…λ‘œλ“œ 될 μ˜ˆμ •μž…λ‹ˆλ‹€. :)
1
star
25

DDPG_mj

DDPG_mj
Python
1
star
26

assignment04

Datamining assignment 04
Jupyter Notebook
1
star
27

-RL-Value_based_summariaztion

이 μ €μž₯μ†ŒλŠ” DQN, DRQN, PER, Rainbow DQNκ³Ό 같은 value-based RL μ•Œκ³ λ¦¬μ¦˜λ“€μ„ μ •λ¦¬ν•˜κ³  직접 κ΅¬ν˜„ν•œ μ†ŒμŠ€μ½”λ“œλ₯Ό κ³΅μœ ν•©λ‹ˆλ‹€.
1
star
28

-RL-Deep_Q_Network

This repository describes the 'Deep Q-Network'. For the improved algorithms, 'Dueling DQN', which divide the action-value function (Q(s, a)) into advantage function (A(a)) and state-value function (v(s)) and 'Double DQN', which has two neural network (primary NN and target NN) will be uploaded as well.
Python
1
star