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

RouteRL is a multi-agent reinforcement learning framework for modeling and simulating the collective route choices of humans and autonomous vehicles.

This project is a pipeline that connects a Matlab simulation (Simulink) to an OpenAI Gym wrapper for PyTorch Reinforcement Learning using the DQN algorithm.

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

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

Small prototype to show RLBench usage with TorchRL

This project aims to improve the efficiency of online reinforcement learning by incorporating bisimulation-based metrics into the experience replay process. Bisimulation Prioritized Experience Replay (BPER) prioritizes experiences based on their behavioral differences.

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

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

MARL research project, where agents must collaboratively solve multi-agent pathfinding tasks in complex, obstacle-rich environments.

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

MARL research project, where agents collaboratively self-organize inside dynamically generated geometric patterns.

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.

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

MARL research project, where agents collaboratively optimize a given objective function in a multi-dimensional search space.

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

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