bandit algorithms

/* python3 numpy matplotlib */

$ python main.py

amir-esi-rad implementation

graph.ipynb

rl-practical.pdf

Name		Name	Last commit message	Last commit date
Latest commit History 16 Commits
.gitignore		.gitignore
LICENSE		LICENSE
MC_simulator.py		MC_simulator.py
README.md		README.md
agent.py		agent.py
agent_factory.py		agent_factory.py
bandit.py		bandit.py
contextual_bandit.py		contextual_bandit.py
enviroment.py		enviroment.py
epsilon_greedy_agent.py		epsilon_greedy_agent.py
esmaili-ohadi-talebi-rl.zip		esmaili-ohadi-talebi-rl.zip
experiment.py		experiment.py
explore_then_exploit_agent.py		explore_then_exploit_agent.py
graph.ipynb		graph.ipynb
main.py		main.py
old_code.py		old_code.py
report.py		report.py
rl-practical.pdf		rl-practical.pdf
successive_elimination_agent.py		successive_elimination_agent.py
ubc1_agent.py		ubc1_agent.py
util.py		util.py