Final project for CS 394R Reinforcement Learning: Theory and Practice
Oguzhan Akcin (oa5983), Po-han Li (pl22767)
| package | version |
|---|---|
| python | 3.9.12 |
| gym | 0.12.1 |
| numpy | 1.20.1 |
| torch | 1.10.2 |
| matplotlib | 3.4.3 |
python test_reinforce.py
Modify the number of sites, data arriving rate, reward structure and capacities of the environment in env.py.
Modify maximum episode, discount factor, and iteration in test_reinforce.py.
test_reinforce.py and reinforce.py are modified from course programming assignment.
For more information, please check: https://www.cs.utexas.edu/~pstone/Courses/394Rspring22/index.html