🚀 Optimize your portfolio with deep reinforcement learning, achieving superior returns and risk management in dynamic asset allocation.

Custom gym environment for training Deep Reinforcement Learning policies to race and drift on 1/10 scale or full-size Ackermann vehicles. SB3 and wandb integration. Based on the f1tenth_gym simulator built by UPenn

🚀 Integrate PX4, ROS 2, and Gazebo for drone SLAM, mapping, and control with LiDAR and RGBD camera support in simulation.

Machine learning library, Distributed training, Deep learning, Reinforcement learning, Models, TensorFlow, PyTorch

Reliable Policy Transfer for Safety-Aware End-to-End Driving with Deep Reinforcement Learning

Paper repository: "Dragonfly: a modular deep reinforcement learning library"

🇺🇾 Uruguayan Truco game engine + library written entirely in Python

Repository that houses the program used to investigate the control of subsystems in homes based on a DRL model. The program uses the EnergyPlus Python API and Ray's Tune and RLlib libraries.

A DRL SAC policy based XAUUSD trading bot

Research synthesis (2022) on Deep Reinforcement Learning & Autonomous Agents: from 2D patterns to 3D Open-World simulations and Sim-to-Real challenges.

Curated list for Deep Reinforcement Learning (DRL): software frameworks, models, datasets, gyms, baselines...

A Deep Reinforcement Learning (PPO) model exported for optimizing VM placement and lifecycle management. Developed by UCD for the EU MLSysOps project.

A pure-Rust reinforcement learning environments library, inspired by Gymnasium.

Deep Reinforcement Learning based Decision-Making in Autonomous Driving Tasks

PPO-based trading agent with automated fine-tuning every 2 hours and SHAP/LIME explainability. Achieved 22.56% return with 2.318 Sharpe ratio.

Deep Reinforcement Learning for mobile robot navigation in IR-SIM simulation. Using DRL (SAC, TD3, PPO, DDPG) neural networks, a robot learns to navigate to a random goal point in a simulated environment while avoiding obstacles.

Setup for working with SO-101 robot arm based on LeRobot library

Deep Reinforcement Learning-assisted Memetic Algorithm for Distributed Flexible Job Shop Scheduling

Mode for optimizing 5G networks latency. Developed by NTT DATA for the EU MLSysOps project.

A Deep Reinforcement Learning (DRL) solution for the Job Scheduling Problem using PPO and Stable Baselines3. Optimized to minimize makespan by balancing workloads across machines in a custom OpenAI Gym environment, outperforming standard heuristic baselines.