프로젝트

articles

The Unseen Hand: Guiding a Virtual Drone with Sparse and Dense Rewards

Exploring training a drone with reinforcement learning, focusing on the trade-offs between sparse and dense rewards to achieve agile flight while avoiding unintended "reward hacking."

Using Reinforcement Learning for Stock Trading with FinRL

Learn stock trading with Reinforcement Learning (RL) and FinRL. This guide covers RL theory, FinRL setup, agent training (DQN, PPO), backtesting, and practical considerations, including code examples and pitfalls.

멀티 에이전트 강화 학습을 사용하여 OpenSpiel의 Connect 4를 Ray의 Rllib으로 플레이하기

셀프 플레이를 사용하여 강화 학습 에이전트가 Connect 4를 마스터하도록 훈련하고 사람의 개입 없이 고급 전략을 달성하는 방법을 알아보세요.

Mastering Autonomy: A Comprehensive Guide to the AutoDRIVE Ecosystem and Reinforcement Learning

A complete guide to the AutoDRIVE ecosystem. Learn to train self-driving car agents from scratch using reinforcement learning in this powerful Unity-based simulator.

강화 학습을 통한 체육관 자동차 경주 문제 해결

강화 학습을 적용하여 Gyum의 Car Racing 게임을 해결하는 방법을 알아보고, 다양한 알고리즘이 어떻게 작동하는지 확인하고, 이산 동작 공간과 연속 동작 공간 중 어느 것이 더 나은지 알아보세요.

강화 학습으로 아타리의 퐁 마스터하기: 희소한 보상 극복과 성과 최적화

RL 요원을 훈련시켜 희박한 보상과 높은 차원의 입력으로 아타리의 퐁 (Atari's Pong) 을 마스터하세요.사전 처리, 리플레이 버퍼, 성능 향상 전략을 살펴보세요.

From Zero to Dino-Roar: Teaching a T-Rex to Walk with MuJoCo and Reinforcement Learning

Build a bipedal T-Rex model in MuJoCo and lay the groundwork for teaching it to walk using reinforcement learning techniques like PPO or SAC. Get the XML, Python setup, and conceptual RL overview

Ultimate Guide to Contextual Bandits: From Theory to Python Implementation

Discover the ultimate guide to contextual bandits, covering everything from core theory and key algorithms to a complete Python implementation with code for building powerful personalization and recommendation systems

Bridging Worlds: How Visual Language Action Models are Teaching Robots to See, Understand, and Act

Understand how Visual Language Action Models (VLAs) let robots follow commands by fusing AI vision and language for action, demonstrated with a conceptual Python robotics simulation

Aligning and Augmenting Intelligence: A Technical Survey of Reinforcement Learning in Large Language Models

Learn how Reinforcement Learning from Human Feedback (RLHF) and emerging techniques like DPO are used to train safer, more helpful, and aligned Large Language Models (LLMs).

Michael Kudlaty



October 1, 2025