spktrm
Follow
Stars
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
A Pokemon battle engine that can search through Pokemon states
A curated list of important published computer vision paper on a weekly basis
A list of inputs that beats Pokemon Platinum
A list of inputs that will beat the vast majority of Pokemon Firered games
A minimal, complete, Pokémon battle simulation engine optimized for performance
Computing AUC ROC from scratch in python without using any libraries
VQVAEs, GumbelSoftmaxes and friends
Playing Pokemon Red with Reinforcement Learning
Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.
A self-play RL system that learns to battle Pokémon on Showdown.
Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…
A PyTorch Platform for Distributed RL
Python 3 and JavaScript interoperability. Successor To PyV8 (https://github.com/flier/pyv8)
The client for Pokémon Showdown
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Reinforcement learning approach to playing competitive Pokémon.
Baseline implementation of recurrent PPO using truncated BPTT
Takes input from other players champions/items, predicts what they build and calculates best team/comp for you
Files from the published Alpha Star paper by DeepMind