ppo-agent

Reinforcement learning tutorials

This repository hosts a customized PPO based agent for Carla. The goal of this project is to make it easier to interact with and experiment in Carla with reinforcement learning based agents -- this, by wrapping Carla in a gym like environment that can handle custom reward functions, custom debug output, etc.

Adversarial attacks on Deep Reinforcement Learning (RL)

Deep Reinforcement Learning for Trading

Multi agent gym environment based on the classic Snake game with implementations of various reinforcement learning algorithms in pytorch

💡 Grasp - Pick-and-place with a robotic hand 👨🏻‍💻

Financial trading strategies using deep reinforcement learning (DRL). It offers a frameworks for quantitative finance, enabling practitioners to create, test, and implement investments strategies.

Official codebase for the preprint: "Representation over Routing: Overcoming Surrogate Hacking in Multi-Timescale PPO".

Reinforcement Learning based navigation

Developed a highly customizable OpenAI gym environment and trained a stable_baselines3 PPO agent. Used the expert agent for Imitation Learning with DAgger

Building an LLM with RLHF involves fine-tuning using human-labeled preferences. Based on Learning to Summarize from Human Feedback, it uses supervised learning, reward modeling, and PPO to improve response quality and alignment.

A deep reinforcement learning Bot for https://kana.byha.top:444/

🚤🏖️BOATS DO VZHHHHH BBBDROOM, BEEEEP, BEEEP, GNAA, HONK, VZHHHHHHHHHHHHHH🏖️🚤

State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping

Concept and development of a walking AT-ST Walker (Starwars) ML-agent.

Modular Reinforcement Learning in PyTorch.

AI agent learns to walk, run, hop and crawl with out any given data using proximal policy optimisation.

MIMARI 9.0 is not a technical analysis bot; it is a mathematical framework that models financial markets as noisy, regime-switching, jump-diffusion, and quantum-like probability distributions.

In this project, I have tried to use DeepRL for optimizing the selection of transactions done by the miner to increase the fee when they execute a block on the chain

This project implements a reinforcement learning-based packet scheduler for a simulated router handling multiple traffic classes (video, voice, and best-effort). The goal is to meet delay-based QoS constraints while minimizing latency, using model-free RL techniques such as Q-Learning.