Skip to content
This repository has been archived by the owner on Jul 22, 2024. It is now read-only.

Code for "Reinforcement Learning with Logical Action-Aware Features for Polymer Discovery" paper accepted at RL4RealLife workshop at ICML 2021

License

Notifications You must be signed in to change notification settings

IBM/logical-agent-driven-polymer-discovery

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Reinforcement Learning with Logical Action-Aware Features for Polymer Discovery

environments, data and experiments for Reinforcement Learning with Logical Action-Aware Features for Polymer Discovery paper

Install material discovery environments

pip install -e md-envs

Extract dataset from zip file

cd data/
unzip polymerDiscovery.zip 
cd ..

Update pickled function in dataset

python scripts/update_pickled_function.py

Test with pretrained model

python scripts/main.py test -f 'logical_with_regressor' -a 'dqn' -m 'models/DQN_logical_with_regressor.model'

Train a model

python scripts/main.py train -f 'logical' -a 'dqn' -o 'models/DQN_logical.model'

Usage

python scripts/main.py train -h

python scripts/main.py test -h

About

Code for "Reinforcement Learning with Logical Action-Aware Features for Polymer Discovery" paper accepted at RL4RealLife workshop at ICML 2021

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages