willi-menapace/atari_reinforcement_learning willi-menapace/atari_reinforcement_learning

  • Stars
    star
    3
  • Rank 3,963,521 (Top 79 %)
  • Language
    Python
  • Created over 5 years ago
  • Updated about 5 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
willi-menapace/atari_reinforcement_learning
github

willi-menapace

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

We use the Rainbow DQN model to build agents that play Ms-Pacman, Atlantis and Demon Attack. We make modifications to the model that allow much faster convergence on Ms-Pacman with respect to Deepmind's original paper and obtain comparable performance.

More Repositories

1

PlayableVideoGeneration

Official Pytorch implementation of "Playable Video Generation", CVPR 2022 (Oral)
Python
142
star
2

PlayableEnvironments

Official PyTorch implementation of "Playable Environments: Video Manipulation in Space and Time", CVPR 2022
Python
69
star
3

acids-clustering-domain-shift

Official Pytorch implementation of ACIDS, ECCV 2020 "Learning to Cluster under Domain Shift"
Python
15
star
4

tennis-court-detection

C++
2
star
5

playable-video-generation-website

HTML
1
star
6

UnEaTN

A small university project developed with SCRUM strategy for the prediction of queues at the canteen. It consists of a web application, REST APIs and a Telegram bot.
JavaScript
1
star
7

Domex

Domex is a smart home system realized as a high school project in collaboration with Simone Lorengo in 2015. We built both the smart devices and all the software stack for the creation of distributed, flexible and fault tolerant wireless sensor networks based on the Zigbee protocol. You can do things such as remotely turn lights on and off, gather sensor data, control heating, add and remove smart devices on the fly, look at historical data through the web portal and so on.
C++
1
star