https://github.com/kristjankorjus/Replicating-DeepMind

Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
https://github.com/kristjankorjus/Replicating-DeepMind

Last synced: about 1 month ago
JSON representation

Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind

• Host: GitHub
• URL: https://github.com/kristjankorjus/Replicating-DeepMind
• Owner: kristjankorjus
• License: gpl-3.0
• Created: 2014-04-01T13:41:35.000Z (about 10 years ago)
• Default Branch: master
• Last Pushed: 2015-02-09T18:08:11.000Z (over 9 years ago)
• Last Synced: 2024-01-24T12:34:04.818Z (4 months ago)
• Language: C++
• Size: 33.2 MB
• Stars: 651
• Watchers: 153
• Forks: 210
• Open Issues: 11
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning2 - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-deep-learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• Deep_Learning - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind
• awesome-ai-safety - Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind

README

        
Replicating-DeepMind

====================

Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind. All the information is in our [Wiki](https://github.com/kristjankorjus/Replicating-DeepMind/wiki).

**Progress:** System is up and running on a GPU cluster with cuda-convnet2. It can learn to play better than random but not much better yet :) It is rather fast but still about 2x slower than DeepMind's original system. It does not have RMSprop implemented at the moment which is our next goal. 

Note 1: You can also check out a popular science article we wrote about the system to [Robohub](http://robohub.org/artificial-general-intelligence-that-plays-atari-video-games-how-did-deepmind-do-it/).

Note 2: Nathan Sprague has a implementation based on Theano. It can do fairly well. See [his github](https://github.com/spragunr/deep_q_rl) for more details.