1.AI4Finance-Foundation / FinRL
FinRL®: Financial Reinforcement Learning. 🔥
- deep-reinforcement-learning
- drl-trading-agents
- stock-trading
- drl-algorithms
- pythorch
- tensorflow2
- +8 more
+1,128 stars
from 15,846 · score 7.03
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
51 repositories by Attention Score · Aug 6, 2026 – Nov 3, 2026 (UTC)
2.Farama-Foundation / Shimmy
PettingZoo and Gymnasium bindings for popular reinforcement learning environments outside of Farama
- deepmind-control-suite
- deepmind-lab
- gymnasium
- reinforcement-learning
- gymnasium-environment
+710 stars
from 222 · score 6.57
3.tensortrade-org / tensortrade
An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.
+676 stars
from 6,580 · score 6.52
4.Farama-Foundation / MAgent2
An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments
+626 stars
from 337 · score 6.44
5.Farama-Foundation / Gymnasium
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
+519 stars
from 12,248 · score 6.25
6.vwxyzjn / cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
- wandb
- reinforcement-learning
- pytorch
- python
- gym
- machine-learning
- +10 more
+455 stars
from 10,178 · score 6.12
7.DLR-RM / stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
- reinforcement-learning
- reinforcement-learning-algorithms
- machine-learning
- gym
- openai
- baselines
- +8 more
+350 stars
from 13,608 · score 5.86
8.Unity-Technologies / ml-agents
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
- reinforcement-learning
- unity3d
- deep-learning
- unity
- deep-reinforcement-learning
- neural-networks
- +1 more
+266 stars
from 19,552 · score 5.59
9.thu-ml / tianshou
An elegant PyTorch deep reinforcement learning library.
- pytorch
- policy-gradient
- dqn
- double-dqn
- a2c
- ddpg
- +13 more
+166 stars
from 10,880 · score 5.12
10.evilsocket / pwnagotchi
(⌐■_■) - Deep Reinforcement Learning instrumenting bettercap for WiFi pwning.
- ai
- deep-reinforcement-learning
- wpa-psk
- handshakes
- bettercap
- deep-learning
- +1 more
+112 stars
from 9,136 · score 4.73
11.learnsyslab / gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
- pybullet
- crazyflie
- robotics
- reinforcement-learning
- quadrotor
- control
- +8 more
+106 stars
from 2,092 · score 4.67
12.Farama-Foundation / PettingZoo
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
- api
- gymnasium
- multi-agent-reinforcement-learning
- reinforcement-learning
- multiagent-reinforcement-learning
+75 stars
from 3,475 · score 4.33
13.PWhiddy / PokemonRedExperiments
Playing Pokemon Red with Reinforcement Learning
+69 stars
from 7,861 · score 4.25
14.openai / baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
+67 stars
from 16,709 · score 4.22
15.huseinzol05 / Stock-Prediction-ModelsArchived
Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations
- lstm
- lstm-sequence
- evolution-strategies
- stock-prediction-models
- seq2seq
- trading-bot
- +9 more
+66 stars
from 9,443 · score 4.20
16.openai / gymArchived
A toolkit for developing and comparing reinforcement learning algorithms.
+60 stars
from 37,170 · score 4.11
17.Farama-Foundation / ViZDoom
Reinforcement Learning environments based on the 1993 game Doom :godmode:
- deep-learning
- reinforcement-learning
- python
- vizdoom
- doom
- examples
- +2 more
+58 stars
from 2,051 · score 4.08
18.google-deepmind / acme
A library of reinforcement learning components and agents
+56 stars
from 4,027 · score 4.04
19.Farama-Foundation / HighwayEnv
A collection of environments for autonomous driving and tactical decision-making tasks
- reinforcement-learning
- autonomous-driving
- gymnasium-environment
+55 stars
from 3,286 · score 4.03
20.google / dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
- rl
- ml
- ai
- tensorflow
+53 stars
from 10,878 · score 3.99
21.VowpalWabbit / vowpal_wabbit
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
- c-plus-plus
- machine-learning
- online-learning
- contextual-bandits
- reinforcement-learning
- active-learning
- +2 more
+53 stars
from 8,680 · score 3.99
+53 stars
from 1,392 · score 3.99
23.sail-sg / envpool
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
- reinforcement-learning
- parallel-processing
- cpp17
- pybind11
- reinforcement-learning-environments
- threadpool
- +10 more
+45 stars
from 1,488 · score 3.83
24.HumanCompatibleAI / imitation
Clean PyTorch implementations of imitation and reward learning algorithms
- reward-learning
- inverse-reinforcement-learning
- imitation-learning
- gymnasium
+43 stars
from 1,769 · score 3.78
25.ddbourgin / numpy-ml
Machine learning, in numpy
- machine-learning
- neural-networks
- topic-modeling
- gaussian-mixture-models
- hidden-markov-models
- gradient-boosting
- +13 more
+36 stars
from 16,289 · score 3.61
26.learnsyslab / safe-control-gym
PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL
- gym
- pybullet
- reinforcement-learning
- control
- safety
- quadrotor
- +6 more
+34 stars
from 898 · score 3.56
27.microsoft / CyberBattleSim
An experimentation and research platform to investigate the interaction of automated agents in an abstract simulated network environments.
+33 stars
from 1,772 · score 3.53
28.Yvictor / TradingGym
Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo.
- trading
- python
- reinforcement-learning
- trading-bot
- trading-platform
- trading-simulator
- +4 more
+27 stars
from 1,901 · score 3.33
29.Toni-SM / skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments
- reinforcement-learning
- python
- deep-learning
- gym
- gymnasium
- machine-learning
- +8 more
+23 stars
from 1,079 · score 3.18
30.facebookresearch / ReAgent
A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)
+21 stars
from 3,705 · score 3.09
31.opendilab / DI-engine
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
- reinforcement-learning
- multiagent-reinforcement-learning
- self-play
- imitation-learning
- inverse-reinforcement-learning
- exploration-exploitation
- +14 more
+21 stars
from 3,626 · score 3.09
32.SerpentAI / SerpentAIArchived
Game Agent Framework. Helping you create AIs / Bots that learn to play any game you own!
- python
- video-games
- artificial-intelligence
- machine-learning
- computer-vision
- framework
- +1 more
+18 stars
from 6,972 · score 2.94
33.tensorlayer / TensorLayer
Deep Learning and Reinforcement Learning Library for Scientists and Engineers
+16 stars
from 7,370 · score 2.83
34.takuseno / d3rlpy
An offline deep reinforcement learning library
- deep-reinforcement-learning
- deep-learning
- pytorch
- offline-rl
+16 stars
from 1,672 · score 2.83
35.rlworkgroup / garage
A toolkit for reproducible reinforcement learning research.
- rl-algorithms
- reproducibility
- pytorch
- tensorflow
+15 stars
from 2,114 · score 2.77
36.tensorflow / agents
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
- reinforcement-learning
- tensorflow
- contextual-bandits
- bandits
- multi-armed-bandits
- tf-agents
- +2 more
+13 stars
from 3,017 · score 2.64
37.nicrusso7 / rex-gym
OpenAI Gym environments for an open-source quadruped robot (SpotMicro)
- openai-gym
- openai-gym-environments
- robotics
- tensorflow
- python3
- pybullet
- +14 more
+11 stars
from 1,096 · score 2.48
38.devsisters / DQN-tensorflow
Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning
+10 stars
from 2,582 · score 2.40
39.keras-rl / keras-rl
Deep Reinforcement Learning for Keras.
+6 stars
from 5,542 · score 1.95
+6 stars
from 3,574 · score 1.95
41.ZhengyaoJiang / PGPortfolio
PGPortfolio: Policy Gradient Portfolio, the source code of "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"(https://arxiv.org/pdf/1706.10059.pdf).
+6 stars
from 1,848 · score 1.95
42.flow-project / flow
Computational framework for reinforcement learning in traffic control
- reinforcement-learning
- traffic-control
- benchmark
- autonomous
- vehicle-control
- sumo
+6 stars
from 1,185 · score 1.95
43.StanfordVL / GibsonEnv
Gibson Environments: Real-World Perception for Embodied Agents
- computer-vision
- robotics
- simulator
- sim2real
- deep-learning
- deep-reinforcement-learning
- +4 more
+6 stars
from 942 · score 1.95
44.kh-kim / stock_market_reinforcement_learning
This project provides a stock market environment using OpenGym with Deep Q-learning and Policy Gradient.
+6 stars
from 794 · score 1.95
+5 stars
from 2,274 · score 1.79
46.openai / roboschoolArchived
DEPRECATED: Open-source software for robot simulation, integrated with OpenAI Gym.
+5 stars
from 2,165 · score 1.79
47.Kismuz / btgym
Scalable, event-driven, deep-learning-friendly backtesting library
- reinforcement-learning
- deep-reinforcement-learning
- gym-environment
- openai-gym
- backtesting-trading-strategies
- algorithmic-trading-library
- +12 more
+5 stars
from 1,031 · score 1.79
48.microsoft / malmoArchived
Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presented by this unique environment. --- For installation instructions, scroll down to *Getting Started* below, or visit the project page for more information:
+4 stars
from 4,263 · score 1.61
49.google / traxArchived
Trax — Deep Learning with Clear Code and Speed
- jax
- numpy
- deep-learning
- deep-reinforcement-learning
- machine-learning
- transformer
- +1 more
+3 stars
from 8,295 · score 1.39
50.Ceruleanacg / Personae
📈 Personae is a repo of implements and environment of Deep Reinforcement Learning & Supervised Learning for Quantitative Trading.
- reinforcement-learning
- supervised-learning
- stock-data
- trading
- paper
- stock
- +2 more
+3 stars
from 1,405 · score 1.39
+1 stars
from 3,129 · score 0.69