RLProject

Training models

The main script is train-model.py which allows a user to train an agent using either supervised learning or REINFORCE.

To finetune a pretrained model use the script finetune.py

Name		Name	Last commit message	Last commit date
Latest commit History 72 Commits
docker		docker
.gitignore		.gitignore
Agent.py		Agent.py
Data.py		Data.py
HKrobustness.py		HKrobustness.py
Logger.py		Logger.py
Model.py		Model.py
MujocoReward.py		MujocoReward.py
README.md		README.md
Recorder.py		Recorder.py
RewardOracle.py		RewardOracle.py
control.bash		control.bash
finetune.bash		finetune.bash
finetune.py		finetune.py
make-plots.py		make-plots.py
reinforce.bash		reinforce.bash
reinforcelr.bash		reinforcelr.bash
train-model.py		train-model.py