The most widely used Python to C compiler

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

All Algorithms implemented in Python

Popular predictive models and optimizers implemented in pure Python.

Google Research

SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

Vectorized interface for reinforcement learning environments

A library of reinforcement learning components and agents

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

JAX-based neural network library

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

Deep Reinforcement Learning research experiment using OpenAI Baselines'

MovieLens recommendation system using reinforcement learning (GYM + PPO)

An Open Source Machine Learning Framework for Everyone

TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

High performance datastore for time series and tick data

TensorFlow Reinforcement Learning

A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.

Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.

Deep Reinforcement Learning toolkit: record and replay cryptocurrency limit order book data & train a DDQN agent