bradlick

Stoix

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

alpaca-py

The Official Python SDK for Alpaca API

evosax

Evolution Strategies in JAX 🦎

learned_optimization

AlphaTrade

JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading

RayEnvWrapper

OpenAi's gym environment wrapper to vectorize them with Ray

shedskin

Shed Skin is a restricted-Python-to-C++ compiler. Read the introduction below to learn about the restrictions.

groove

Official implementation for the NeurIPS 2023 paper "Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design"

pybroker

Algorithmic Trading in Python with Machine Learning

warp-drive

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

FinRL

FinRL: Financial Reinforcement Learning. 🔥

sbx

SBX: Stable Baselines Jax (SB3 + Jax)

envpool

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

FinRL-Meta

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

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

ElegantRL

Massively Parallel Deep Reinforcement Learning. 🔥

MicroRTS

A simple and highly efficient RTS-game-inspired environment for reinforcement learning

google-research

Google Research

vectorbt

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

recurrent-ppo-truncated-bptt

Baseline implementation of recurrent PPO using truncated BPTT

episodic-transformer-memory-ppo

Clean baseline implementation of PPO using an episodic TransformerXL memory

curiousreplay

Implementations of Curious Replay for model-based adaptation.

phasic-policy-gradient

Code for the paper "Phasic Policy Gradient"

muzero-general

MuZero

backtesting.py

:mag_right: :chart_with_upwards_trend: :snake: :moneybag: Backtest trading strategies in Python.

colab-github

Authenticate with GitHub in Google Colab to access private repo.

go-explore

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

gym-mtsim

A general-purpose, flexible, and easy-to-use simulator alongside an OpenAI Gym trading environment for MetaTrader 5 trading platform (Approved by OpenAI Gym)

EfficientZero

Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

panda

code powering the comma.ai panda