InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now. Learn more →
Top 23 Python reinforcement-learning Projects
-
nn
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
-
InfluxDB
InfluxDB – Built for High-Performance Time Series Workloads. InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now.
-
Ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Not currently, but it is being worked on https://github.com/ray-project/ray/issues/53976.
-
d2l-en
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
-
reinforcement-learning-an-introduction
Python Implementation of Reinforcement Learning: An Introduction
-
stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
-
Gymnasium
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
-
wandb
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
Project mention: Best Practices for Ensuring AI Agent Performance and Reliability | dev.to | 2025-07-22Use tools like Weights & Biases, Labelbox, or Maxim’s data engine to version your datasets, track changes, and continuously add new edge cases and user feedback.
-
Stream
Stream - Scalable APIs for Chat, Feeds, Moderation, & Video. Stream helps developers build engaging apps that scale to millions with performant and flexible Chat, Feeds, Moderation, and Video APIs and SDKs powered by a global edge network and enterprise-grade infrastructure.
-
-
OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
-
cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
-
-
PaLM-rlhf-pytorch
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
-
Microsoft's agent-lightning project offers a comprehensive toolkit aimed at accelerating the process of building, testing, and deploying AI Agents. This open-source initiative highlights the industry's commitment to enabling faster development and implementation of advanced AI capabilities, providing developers with robust resources to streamline AI agent creation.
-
-
-
trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
-
dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
-
-
-
-
pytorch-a2c-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
-
-
DI-engine
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
NOTE:
The open source projects on this list are ordered by number of github stars.
The number of mentions indicates repo mentiontions in the last 12 Months or
since we started tracking (Dec 2020).
Python reinforcement-learning discussion
Python reinforcement-learning related posts
-
Learning to Model the World with Language
-
maze VS pi-optimal - a user suggested alternative
2 projects | 30 Oct 2025 -
Daily Artificial Intelligence Digest - Oct 26, 2025
-
Train AI agents with reinforcement learning (no code changes needed)
-
Deep Learning from Scratch, the NumPy Way
-
Introduction to Multi-Armed Bandits
-
Launch HN: RunRL (YC X25) – Reinforcement learning as a service
-
A note from our sponsor - InfluxDB
www.influxdata.com | 15 Nov 2025
Index
What are some of the best open-source reinforcement-learning projects in Python? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | nn | 64,273 |
| 2 | Ray | 39,825 |
| 3 | d2l-en | 26,601 |
| 4 | reinforcement-learning-an-introduction | 14,386 |
| 5 | stable-baselines3 | 12,011 |
| 6 | Gymnasium | 10,611 |
| 7 | wandb | 10,521 |
| 8 | machine_learning_examples | 8,742 |
| 9 | OpenRLHF | 8,360 |
| 10 | cleanrl | 8,272 |
| 11 | pysc2 | 8,189 |
| 12 | PaLM-rlhf-pytorch | 7,869 |
| 13 | agent-lightning | 7,818 |
| 14 | TensorLayer | 7,376 |
| 15 | keras-rl | 5,556 |
| 16 | trlx | 4,709 |
| 17 | dm_control | 4,314 |
| 18 | stable-baselines | 4,309 |
| 19 | ElegantRL | 4,221 |
| 20 | acme | 3,842 |
| 21 | pytorch-a2c-ppo-acktr-gail | 3,818 |
| 22 | polyaxon | 3,684 |
| 23 | DI-engine | 3,540 |
Sponsored
InfluxDB – Built for High-Performance Time Series Workloads
InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now.
www.influxdata.com