Modularized Implementation of Deep RL Algorithms in PyTorch

A Torch Based RL Framework for Rapid Prototyping of Research Papers

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.

TensorFlow implementation of Deep RL (Reinforcement Learning) papers based on deep Q-learning (DQN)

RL based agent for atari games

DQN, Double DQN, Dueling Network

Deep reinforcement learning agent

Reinforcement Learning Playground

Using the DRL algorithms put forward by Deepmind to play Atari 2600 Games with a comparison of algorithm performance

Deep Reinforcement Learning: Value-Based methods. An implementation of DQN, DDQN, Dueling Architectures, DQV, DQV-Max on the PyTorch Lightning framework.

Open AI gym lunar-lander solution using Deep Q-Learning Network Architectures

Intelligent elevator scheduling using QR-DQN with Dueling Networks and Prioritized Experience Replay. Achieves ~38% improvement over SCAN baseline. Published at IEEE AICAPS 2026. DOI: 10.1109/AICAPS68631.2026.11452978

A university project where we implement and experiment with different Reinforcement Learning algorithms and trying to optimize the CartPole environment from OpenAI Gym.

Example Dueling DQN implementation with ReLAx

A RL agent that learns to play doom's deadly corridor based on DDQN and PER.