tanzeyy / Prioritized_n-step_DoubleDQN Public

Notifications You must be signed in to change notification settings
Fork 0
Star 1

PyTorch implementation of prioritized n-step double DQN

1 star 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
imgs		imgs
utils		utils
README.md		README.md
agent.py		agent.py
model.py		model.py
train.py		train.py

Repository files navigation

Prioritized n-step Double DQN

PyTorch implementation of n-step double DQN with prioritized replay memory.

Experiments

MoutainCar-V0
- orange, light blue: step = 1
- red: step = 5
- blue: step = 10

Acrobot-v1
- n-step from up to bottom: 10, 5, 3, 1

Requirements

PyTorch==1.7.0

About

PyTorch implementation of prioritized n-step double DQN

Report repository

Releases

No releases published

Packages

No packages published

Contributors 2

Languages

Python 100.0%