GitHub - lionelkiel/RL3: Reinforcement Learning Assignment 3

lionelkiel / RL3 Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Reinforcement Learning Assignment 3

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 17 Commits
__pycache__		__pycache__
.gitattributes		.gitattributes
Experiments.py		Experiments.py
Policy.py		Policy.py
README.txt		README.txt
network_params_ac.pickle		network_params_ac.pickle
network_params_reinforce.pickle		network_params_reinforce.pickle
params_ac.pickle		params_ac.pickle
params_reinforce.pickle		params_reinforce.pickle

Repository files navigation

To get info of the possible arguments run: python Experiments.py
To tune the parameters run: python Experiments.py --method <METHOD> -tune <Network settings to tune (int)> **kwargs
To compare AC with REINFORCE run: python Experiments.py --method <any> -comparison 1 **kwargs
To run the ablation run: python Experiments.py --method <METHOD> -ablation 1 **kwargs
If no optional arguments are given, the best settings of the previously performed tuning are used.