GitHub - harooks/Reinforcement_Learning: Q-learning vs double Q-learning

Name		Name	Last commit message	Last commit date
Latest commit History 27 Commits
Final Project		Final Project
.DS_Store		.DS_Store
Matigon.pdf		Matigon.pdf
Qlearning.py		Qlearning.py
agent_a.py		agent_a.py
boutilier(k=0).png		boutilier(k=0).png
boutilier(k=100)_1.png		boutilier(k=100)_1.png
boutilier(k=100)_2.png		boutilier(k=100)_2.png
climb_game.png		climb_game.png
double-q-learning.pdf		double-q-learning.pdf
double-q-learning.py		double-q-learning.py
fully_stochastic.png		fully_stochastic.png
partially_stochastic.png		partially_stochastic.png
penalty(k=-100).png		penalty(k=-100).png
penalty_game(k=0).png		penalty_game(k=0).png
penalty_game(k=100).png		penalty_game(k=100).png
q_learn_tm.py		q_learn_tm.py
qlearning.csv		qlearning.csv

Provide feedback