Pinned Repositories
reinforcement-learning
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
arboretum
Gradient Boosting powered by GPU(NVIDIA CUDA)
CS294-112-assignments
Assignments for CS294-112.
data-science-bowl-2017
Algorithms for improving lung cancer detection with deep learning
evolution-strategies-exploration
Contains implementation of: Tim Salimans Et al. “Evolution Strategies as a Scalable Alternative to Reinforcement Learning”. Arxiv.org. https://arxiv.org/pdf/1703.03864.pdf.
jovsatools
my personal toolbox 🧰
jtorch
An automatic differentiation engine for personal exploration and learning
rl-examples-sutton-and-barto-book
Python Example from the book "Reinforcement Learning: An Introduction"
speed-challenge-2017
Explore how well deep neural networks perform at predicting vehicle speed given just visual data (dashcam video) containing highway and suburban driving.
jovsa's Repositories
jovsa/jtorch
An automatic differentiation engine for personal exploration and learning
jovsa/jovsa.github.io
jovsa/alpha-zero-general
A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more
jovsa/ANN-playground
A playground to learn and explore techniques about ANN
jovsa/carbs
Cost aware hyperparameter tuning algorithm
jovsa/cut-the-knot-probability-riddles
jovsa/diplomacy_cicero
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
jovsa/dreamerv3
Mastering Diverse Domains through World Models
jovsa/dreamerv3-torch
Implementation of Dreamer v3 in pytorch.
jovsa/kaggle-connect-x
https://www.kaggle.com/c/connectx
jovsa/keymaker
where 🔑s get made
jovsa/mctx
Monte Carlo tree search in JAX
jovsa/meltingpot
A suite of test scenarios for multi-agent reinforcement learning.
jovsa/micrograd
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
jovsa/minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
jovsa/mmd
Code for magnetic mirror descent.
jovsa/mmd-dilated
An implementation of the QRE solver magnetic mirror descent with dilated entropy (MMD).
jovsa/open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
jovsa/openr
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
jovsa/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
jovsa/rebel
An algorithm that generalizes the paradigm of self-play reinforcement learning and search to imperfect-information games.
jovsa/safe-haven-reproduction
jovsa/stream-of-search
Repository for the paper Stream of Search: Learning to Search in Language
jovsa/SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.
jovsa/systems
systems is a set of tools for describing, running and visualizing systems diagrams.
jovsa/Tensor-Puzzles
Solve puzzles. Improve your pytorch.
jovsa/tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️
jovsa/triton
Development repository for the Triton language and compiler
jovsa/trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
jovsa/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs