Installation

This repo contains the code for the paper "Reinforcement Learning for Dynamic Memory Allocation" - https://www.overleaf.com/read/grcgrdrwxhyy#45e67d

Running the Code

To run experiment 1 from the paper, execute the following command: python experiment1.py

If you would like to retrain from scratch, follow these steps:

Comment out line 24 in experiment1.py, which loads a previously trained model.
Uncomment lines 31 and 32 in experiment1.py for training.

To run experiments 2 and 3 from the paper, open test_pol_sb3.ipynb.

To get the ith graph of experiment j:

Uncomment the 6 lines of code in the second cell which have the experiment i graph j commented above it.

Run the full notebook to get each individual graph

Name		Name	Last commit message	Last commit date
Latest commit History 30 Commits
__pycache__		__pycache__
allocators		allocators
demo_logs		demo_logs
environments		environments
models		models
policies		policies
request_streams		request_streams
results		results
trajectories		trajectories
.gitignore		.gitignore
README.md		README.md
Reinforcement Learning for Memory Allocation.pdf		Reinforcement Learning for Memory Allocation.pdf
console.ipynb		console.ipynb
experiment1.py		experiment1.py
page.py		page.py
requirements.txt		requirements.txt
sb_value_function_kwargs.py		sb_value_function_kwargs.py
test_allocators.py		test_allocators.py
test_pol.ipynb		test_pol.ipynb
test_pol.py		test_pol.py
test_pol_sb3.ipynb		test_pol_sb3.ipynb