DEEP Q NETWORK IMPLEMENTATION FOR FIGHTINGICE GAME
Reinforcement Learning is one of machine learning study where agents try to take action to maximize cumulative rewards. For that purpose, the agent saves the expected reward inside QTable. The need for memory for Q-Table can be replaced by using neural network to predict the Q-Value. This method is...
Saved in:
Main Author: | Fathur Rahman, Muhammad |
---|---|
Format: | Final Project |
Language: | Indonesia |
Online Access: | https://digilib.itb.ac.id/gdl/view/43577 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Institut Teknologi Bandung |
Language: | Indonesia |
Similar Items
-
OPTIMIZED URBAN TRAFFIC CONTROL WITH ADAPTIVE EXPONENTIAL REWARD DEEP Q NETWORK AT INTERSECTION USING PARTICLE SWARM OPTIMIZATION
by: Aditya Rahman, Muhammad -
TRAFFIC CONTROL BASED ON DEEP Q-NETWORK ALGORITHM WITH ADAPTIVE REWARD MECHANISM IN INTERSECTION NETWORK
by: Riza Tanwirul Fuad, Muhammad -
State-Aware Variational Thompson Sampling for Deep Q-Networks
by: WEE SUN LEE, et al.
Published: (2021) -
TRAFFIC CONTROL BASED ON DEEP Q-NETWORK ALGORITHM WITH ADAPTIVE REWARD MECHANISM IN INTERSECTION NETWORK
by: Okto Fernandez, Eric -
Dynamic flexible job shop scheduling using double deep Q-network
by: Chua, Hui Shun
Published: (2021)