GitHub - swanky-rt/Reinforcement-Learning: This is part of coursework 687( RL) at UMass Amherst

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
.idea		.idea
Monte_Carlo		Monte_Carlo
Mountain_Car		Mountain_Car
Stranger_Things(Upside Down)_MDP		Stranger_Things(Upside Down)_MDP
TD_Learning		TD_Learning
__pycache__		__pycache__
value_iteration		value_iteration
.DS_Store		.DS_Store
Archive.zip		Archive.zip
Q2.a.py		Q2.a.py
Q2.b.py		Q2.b.py
Q2.c.py		Q2.c.py
Q2.d.py		Q2.d.py
ReadMe		ReadMe
estimation.py		estimation.py
exact_evaluation.py		exact_evaluation.py
mdp_implementation.py		mdp_implementation.py
plot.py		plot.py
policy.py		policy.py
q2a_running.csv		q2a_running.csv
q2c_compare_gamma.csv		q2c_compare_gamma.csv
q2c_compare_gamma.png		q2c_compare_gamma.png
q2d_policy_search_results.csv		q2d_policy_search_results.csv
random_generator.py		random_generator.py
simulation.py		simulation.py

Repository files navigation

This is the part of coursework. Here I have designed many MDPs, RL learning algorithms without using existing libraries.

This is part of coursework 687( RL) at UMass Amherst

No releases published