Official JAX implementation of xLSTM including fast and efficient training and inference code. 7B model available at https://huggingface.co/NX-AI/xLSTM-7b.

120+ interactive Python coding interview challenges (algorithms and data structures). Includes Anki flashcards.

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

The Official Python SDK for Alpaca API

An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.

Orbax provides common checkpointing and persistence utilities for JAX users

Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.

Evolution Strategies in JAX 🦎

Code for Go-Explore: a New Approach for Hard-Exploration Problems

A library of reinforcement learning components and agents

🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL

Implementations of Curious Replay for model-based adaptation.

Repository for Iterated Relearning: The Impact of Non-stationarity on Generalisation in Deep Reinforcement Learning

Code for the paper "Phasic Policy Gradient"

Find your trading edge, using the fastest engine for backtesting, algorithmic trading, and research.

Portfolio analytics for quants, written in Python

Really Fast End-to-End Jax RL Implementations

Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Algorithmic Trading in Python with Machine Learning

FinRL­®-Meta: Dynamic datasets and market environments for FinRL.

FinRL®: Financial Reinforcement Learning. 🔥

SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms

Clean baseline implementation of PPO using an episodic TransformerXL memory

This repository contains implementations and illustrative code to accompany DeepMind publications

Baseline implementation of recurrent PPO using truncated BPTT

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.