torchrl
There are 0 repository under torchrl topic.
ai4co / rl4co
A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)
Language:Python 716BricksRL / bricksrl
BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO
Language:Python 64- RouteRL
COeXISTENCE-PROJECT / RouteRL
RouteRL is a multi-agent reinforcement learning framework for modeling and simulating the collective route choices of humans and autonomous vehicles.
Language:Jupyter Notebook 27 Spinkoo / Matlab2TorchRL
This project is a pipeline that connects a Matlab simulation (Simulink) to an OpenAI Gym wrapper for PyTorch Reinforcement Learning using the DQN algorithm.
Language:MATLAB 21elte-collective-intelligence / student-level-based-foraging
Multi-Agent Reinforcement Learning for Level-Based Foraging Using TorchRL.
SchweizerischeBundesbahnen / flatland-torchrl
An adaption of the Flatland environment for TorchRL.
Language:Python 5MARL research project, where agents collaboratively self-organize inside dynamically generated geometric patterns.
Language:Python 2MARL research project in which rescuer and rescuee agents collaborate to navigate and succeed in complex, obstacle-rich environments.
Language:Python 2- Language:Python 2
- modularl
zakaria-narjis / modularl
A highly modular and extensible PyTorch-based reinforcement learning library.
Language:Python 2 AlexandreBrown / RLBench-TorchRL-Prototype
Small prototype to show RLBench usage with TorchRL
Language:Python 1Small prototype to show RoboHive usage with TorchRL for visual deep reinforcement learning
Language:Python 1bielnebot / rl_implementations
🤖 PPO and DQN reinforcement learning algorithms implemented with PyTorch and TorchRL for autonomous driving.
Language:Python 1MARL research project, based on the famous board game "Scotland Yard".
Language:Python 1MARL research project, where agents collaboratively optimize a given objective function in a multi-dimensional search space.
Language:Python 1MARL research project, where agents must collaboratively solve multi-agent pathfinding tasks in complex, obstacle-rich environments.
Language:Jupyter Notebook 1A 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.
Language:Python 1MARL research project, where multiple agents (ants) interact in a shared 2D environment containing scattered items of different categories.
Language:Python 1nabilshadman / deep-reinforcement-learning-automated-trading-hpc
Application of deep reinforcement learning (DQN and PPO) for automated trading on HPC system, comparing performance across CPU/GPU nodes
Language:Python 1Titouaaaan / RL-Souls
Using Reinforcement Learning to play Dark Souls III
Language:Python 1ZosoV / final_project
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.
Language:Jupyter Notebook 1Inspired by the series "Squid Game", this project requires agents to learn coordinated decision-making and spatial negotiation in a competitive-cooperative setting.
Language:Python 0mikemykhaylov / marsMarsRL
Clone of the Mars: Mars game using Pygame as a Reinforcement Learning Gym 🚀
Language:Python 0AmalDevHaridevan / envpool_wrapper
Envpool wrapper for Envs written in Python. This module defines a protocol, allowing to wrap aribitrary environments written in Python to be executed using envpool.
Language:C++denizetkar / chess-rl-test
Training a PPO agent to play chess with pretraining and self-learning using PyTorch Lightning and TorchRL
Language:Python
