🤖 Explore reinforcement learning techniques with projects including a taxi agent using Q-Learning and a DQN-based Space Invaders agent.

🤖 Implement classic and state-of-the-art deep reinforcement learning algorithms using clear PyTorch code for easy understanding and application.

Clean RL algorithm implementations in under 100 lines each.

Deep reinforcement learning for smart calibration of radio telescopes. Automatic hyper-parameter tuning.

Implementation and usage of advanced deep reinforcement learning algorithms in robotic control and complex simulated environments.

Comprehensive collection of reinforcement learning algorithms implemented from scratch in PyTorch. Features tabular methods, value-based , policy gradient, actor-critic, offline RL, and multi-agent methods Includes YAML-based configuration, W&B integration, and unified CLI.

[ICLR 2026 oral] Official Repository for The Paper, Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?

R²PA — Regime-aware reinforcement learning for portfolio allocation (RL, regime signals, LLM oracle)

Official Repository for The Paper, Beyond Multi‑Agent Reinforcement Learning: Scalable Centralized Control for Large-Scale Dynamic Trip-Vehicle Assignment

PPO-based trading agent with automated fine-tuning every 2 hours and SHAP/LIME explainability. Achieved 22.56% return with 2.318 Sharpe ratio.

Deep Reinforcement Learning for mobile robot navigation in IR-SIM simulation. Using DRL (SAC, TD3, PPO, DDPG) neural networks, a robot learns to navigate to a random goal point in a simulated environment while avoiding obstacles.

A clean PyTorch implementation of PPO, SAC, and TD3 made from scratch. It is built for testing and comparing continuous control RL algorithms on complex environments such as BipedalWalker-v3.

A beginner-friendly repository on Deep Reinforcement Learning (RL), written in PyTorch.

Quadruped gait control using reinforcement learning (TD3, DDPG) with MATLAB/Simulink and Simscape simulation.

Paper repository: "Dragonfly: a modular deep reinforcement learning library"

For this paper RLlib has two version 2.10 and 2.8. in Version 2.10 we do not have TD3 so we use version 2.8. In higher version we cannot use manually the policy of trained agents. Reward function has deliberately removed!

An open source deep learning library for Unity.

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

Autonomous Robotic Arm Control (Franka Panda) using Twin Delayed DDPG (TD3) in Robosuite/MuJoCo. An implementation of Deep Reinforcement Learning for continuous control tasks like Door Opening.