CS294-112 HW 3: Q-Learning

Dependencies:

Before doing anything, first replace gym/envs/box2d/lunar_lander.py with the provided lunar_lander.py file.

The only files that you need to look at are dqn.py and train_ac_f18.py, which you will implement.

See the HW3 PDF for further instructions.

The starter code was based on an implementation of Q-learning for Atari generously provided by Szymon Sidor from OpenAI.

Name		Name	Last commit message	Last commit date
Latest commit History 122 Commits
.pylint.d		.pylint.d
Assignment1_archive		Assignment1_archive
Assignment2_archive		Assignment2_archive
.gitignore		.gitignore
LICENSE.md		LICENSE.md
README.md		README.md
atari_wrappers.py		atari_wrappers.py
dqn.py		dqn.py
dqn_utils.py		dqn_utils.py
logz.py		logz.py
lunar_lander.py		lunar_lander.py
plot.py		plot.py
requirements.html		requirements.html
requirements.txt		requirements.txt
run_dqn_atari.py		run_dqn_atari.py
run_dqn_lander.py		run_dqn_lander.py
run_dqn_ram.py		run_dqn_ram.py
test.py		test.py
train_ac_f18.py		train_ac_f18.py

jeremymatt/CS395_homework