Miffyli - Overview (original) (raw)

View Miffyli's full-sized avatar

Anssi Miffyli

Researcher at Meta Fundamental Artificial Intelligence Research (FAIR), working on reinforcement learning.

Organizations

@The-Codebomb @Stable-Baselines-Team

Block or report Miffyli

Pinned Loading

  1. PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
    Python 10.5k 1.8k
  2. Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
    Python 1.4k 146
  3. MineRL Competition for Sample Efficient Reinforcement Learning - Python Package
    Java 779 161
  4. Behavioural cloning solution to MineRL2020 competition
    Python 17 8
  5. Experiment code for testing effect of various action space transformations in reinforcement learning
    Python 30 2
  6. Code for the experiments done in the paper "GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters"
    Python 24 8