Concise pytorch implements of DRL algorithms, including REINFORCE, A2C, DQN, PPO(discrete and continuous), DDPG, TD3, SAC.

A PyTorch library for building deep reinforcement learning agents.

DQN-Atari-Agents: Modularized & Parallel PyTorch implementation of several DQN Agents, i.a. DDQN, Dueling DQN, Noisy DQN, C51, Rainbow, and DRQN

Deep Q-Learning (DQN) implementation for Atari pong.

A PyTorch Implementation of "Optimization of Molecules via Deep Reinforcement Learning".

A Torch Based RL Framework for Rapid Prototyping of Research Papers

Graph-based Deep Q Network for Web Navigation

Important Note fastrl version 2 is being developed at fastrl. Note the link in the readme

SUMO Pytorch Deep Reinforcement Learning Traffic Signal Control

PyTorch implementation of the state-of-the-art distributional reinforcement learning algorithm Fully Parameterized Quantile Function (FQF) and Extensions: N-step Bootstrapping, PER, Noisy Layer, Dueling Networks, and parallelization.

Multi-agent reinforcement learning framework

Solving Atari Pong Game w/ Duel Double DQN in Pytorch

This code is the result of the collaboration of RL Turkey team.

PyTorch agents and tools for (Deep) Reinforcement Learning

Reinforcement Learning - Implementation of Exercises, algorithms from the book Sutton Barto and David silver's RL course in Python, OpenAI Gym.

Implementation of Deep Reinforcement Learning algorithms in the Unity game engine.

Reinforcement Learning for Optimal inventory policy

Integrate AutoRL into DQN to implement a single traffic signal control system.

PyTorch implementation of DQN, DDQN and Dueling DQN to solve Atari games including PongNoFrameskip-v4, BreakoutNoFrameskip-v4 and BoxingNoFrameskip-v4