reward-functions

在A股(股票)市场上训练强化学习交易智能体

AWS DeepRacer Free Student Workshop: Run faster by using your custom waypoints. Step by Step to learn reinforcement learning,

Compilation of reward functions for the AWS Deep Racer service

A reinforcement learning model specialized in stock prediction utilizing deep learning techniques, incorporating reward mechanisms, compatible with any machine equipped with Python.

My AWS DeepRacer reward functions and some analysises

Some of my reward functions and analysis that helped me throughout my learning

Robotic Arm learns to approach objects using Deep Reinforcement Learning

AWS Networking Organisation Internal DeepRacer Cup 2020

Group Relative Policy Optimization (GRPO) implementations - NanoAhaMoment, GRPO:Zero, Simple GRPO, and GRPO from Scratch - spanning vLLM + DeepSpeed, custom Transformer stack, Bottle HTTP reference server, and pure PyTorch. Compares generation backends, reference policy strategies, reward designs, and loss functions on GSM8K and Countdown tasks.

Graduation Project 2023, an intelligent traffic management system that combines reinforcement learning along with simulation.

Pre-print version of "Assessment of Reward Functions in Reinforcement Learning for Multi-Modal Urban Traffic Control under Real-World limitations"

Empowering Rewards and Governance for Our Projects and Products.

제3회 대한민국 인공지능(AI) 융합 자율주행 경진대회 3위🏆

Interactive reward function creation and analysis for an AI agent to play the game of Super Mario

Presented in IEEE 23rd International Conference in Systems, Man, and Cybernetics. Pre-print version of "Assessment of Reward Functions for Reinforcement Learning Vehicular Traffic Signal Control Under Real-World Limitations"

Dein All-in-One Server-Tool für mehr Interaktion, Spaß und Ordnung. Automatisierte Willkommensnachrichten, Reaktionsrollen, Musik, Belohnungssysteme und nützliche Moderation – alles in einem Bot.

Aplicación de navegación GPS 3D multiplataforma (PWA, iOS, Android) construida con Ionic/Angular y un backend inteligente en Node.js para procesamiento de datos en tiempo real, map-matching con Valhalla y optimización con PostgreSQL y Memcached.

BAT Basic Attention Token, Brave, Uphold, DAPP, Cryptocurrenies.

Building an Autonomous Maze Solver using reinforcement learning to train agents for decision-making in dynamic grid-based environments

This is the submission for the Deep Past Challenge posted on Kaggle, that attempts in building a translation system to decode all Assyrian cuneiforms