cgreer / alpha-zero-boosted
A "build to learn" Alpha Zero implementation using Gradient Boosted Decision Trees (LightGBM)
☆84Updated 4 years ago
Related projects: ⓘ
- Cellular automaton-based calculus for the masses☆23Updated 6 years ago
- Reinforcement learning in TensorFlow 2☆22Updated 2 years ago
- High performance implementation of Deep neuroevolution in pytorch using mpi4py. Intended for use on HPC clusters☆24Updated 2 years ago
- Celular automaton-based calculus for the masses☆110Updated 4 years ago
- A fast Tsetlin Machine implementation employing bit-wise operators, with MNIST demo.☆64Updated 5 years ago
- 1.2% test error on MNIST using only least squares and numpy calls.☆16Updated last year
- 🦠 AD in less than 20 lines☆48Updated 3 years ago
- Markov Decision Processes in Python☆15Updated 5 years ago
- LLMs playing chess are sensitive to how the position came to be☆18Updated 7 months ago
- convert a scikit-learn decision tree into a Keras model☆39Updated 10 months ago
- Rudimentary automatic differentiation framework☆73Updated 5 years ago
- An experiment with "freely" wired neural networks (no layers)☆163Updated last month
- Minimal deep learning library written from scratch in Python, using NumPy/CuPy.☆116Updated 2 years ago
- A Symbolic Regression engine☆29Updated 3 years ago
- A set of neuroevolution experiments with/towards deep networks☆125Updated 4 years ago
- ☆45Updated this week
- Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings☆76Updated 2 years ago
- ☆20Updated 3 years ago
- Probabilistic programming system for fast and exact symbolic inference☆76Updated 2 months ago
- Code for "Meta Learning Backpropagation And Improving It" @ NeurIPS 2021 https://arxiv.org/abs/2012.14905☆31Updated 2 years ago
- Designing bridge trusses with Pytorch autograd☆60Updated 7 months ago
- Open-source library for a reinforcement learning research.☆54Updated last year
- OpenAI gym environment for evolving morphologies of 2D virtual creatures.☆32Updated last year
- Grow virtual creatures in static and physics simulated environments.☆52Updated 5 months ago
- Evolution Strategy Library☆55Updated 4 years ago
- Adapting the AlphaZero algorithm to remove the need of execution traces to train NPI.☆77Updated 11 months ago
- A runtime shape checker and auto-annotator for tensor programs (pronounced "stanley")☆39Updated 4 years ago
- Advent of Code in pure TensorFlow☆27Updated last year
- Probabilistic Programming eXecution protocol (PPX)☆74Updated 2 years ago
- ☆19Updated 3 years ago