Anssi
Miffyli
Researcher at Meta Fundamental AI Research (FAIR), working on reinforcement learning.
Languages
Top Repositories
Python tools for creating suitable dataset for OpenAI's im2latex task: https://openai.com/requests-for-research/#im2latex
Toribash Learning Environment
Website for detailed game mechanics
Experiment code for testing effect of various action space transformations in reinforcement learning
Code for the experiments done in the paper "GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters"
Repositories
40Toribash Learning Environment
✏️ Storyboarder makes it easy to visualize a story as fast you can draw stick figures.
Website for detailed game mechanics
Submission code of UEFDRL team to NeurIPS 2019 MineRL challenge (5th place)
Python tools for creating suitable dataset for OpenAI's im2latex task: https://openai.com/requests-for-research/#im2latex
Behavioural cloning solution to MineRL2020 competition
Code for the experiments done in the paper "GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters"
🧠🗼
The source code for mastering the game of Chutes and Ladders
No description provided.
A Terraria TSchock server plugin that allows customizing which items are dropped upon death
Evaluating different engineering tricks that make RL work
A self-paced course to learn Rust, one exercise at a time.
Experiment code for testing effect of various action space transformations in reinforcement learning
Open Source real-time strategy game engine for early Westwood games such as Command & Conquer: Red Alert written in C# using SDL and OpenGL. Runs on Windows, Linux, *BSD and Mac OS X.
Creating fixed-length vectors to describe RL/GA policies
Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
Collection of in-progress libraries for entity neural networks.
Code for Gym documentation website
Optimizing speaker verification and spoofing countermeasure systems together with REINFORCE
A JSON viewer using pure python
A toolkit for developing and comparing reinforcement learning algorithms.
Train an agent to play VizDoom with multi sensory inputs. Trained using sample factory
No description provided.
Source code for the experiments in my MSc thesis titled Understanding Forgetting in Artificial Neural Networks.
No description provided.
Infinite adventures await!
The Machine Learning Toybox for testing the behavior of autonomous agents.
PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.