A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)

BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO

An adaption of the Flatland environment for TorchRL.

A highly modular and extensible PyTorch-based reinforcement learning library.

Small prototype to show RoboHive usage with TorchRL for visual deep reinforcement learning

Small prototype to show RLBench usage with TorchRL

Using Reinforcement Learning to play Dark Souls III

Application of deep reinforcement learning (DQN and PPO) for automated trading on HPC system, comparing performance across CPU/GPU nodes

Multi-Agent Reinforcement Learning for TurtleBot3 Using ROS2 Humble and Gazebo.

Clone of the Mars: Mars game using Pygame as a Reinforcement Learning Gym 🚀

MARL research project in which rescuer and rescuee agents collaborate to navigate and succeed in complex, obstacle-rich environments.

MARL research project, where multiple agents (ants) interact in a shared 2D environment containing scattered items of different categories.

MARL research project, based on the famous board game "Scotland Yard".

A Multi-Agent Reinforcement Learning (MARL) research project where patrolling and intruder agents engage in an adversarial setting, continuously adapting and countering each other’s strategies.

Inspired by the series "Squid Game", this project requires agents to learn coordinated decision-making and spatial negotiation in a competitive-cooperative setting.

🤖 PPO and DQN reinforcement learning algorithms implemented with PyTorch and TorchRL for autonomous driving.

Training a PPO agent to play chess with pretraining and self-learning using PyTorch Lightning and TorchRL