Implementation of Proximal Policy Optimization algorithm on a custom Unity environment.

DDPG and D4PG Continuous Control

Multi-Agent Reinforcement Learning: Collaboration and Competition

Multiagents learning to play the game of tennis with the goal being to get an average score of +0.5 (over 100 consecutive episodes, after taking the maximum over both agents)

This repo contains various build versions of my Boat Attack with ML-Agents repo.

The following is my submission for the Seventh Semester Project II. It incorporates Reinforcement Learning to Create an Adversarial Flight Simulation in Unity

To train a rollerball using DRL algorithms, including PPO, DDPG

심층강화학습기반 장애물과 신호등을 고려한 다차선 자율주행 연구 (한국통신학회 논문지 2024-6월호)

Repository for my project (Collaboration and Competition) with Deep Reinforcement Learning

Udacity Deep Reinforcement Learning Nanodegree Projects

Repository for my project (Bananas Collector) with Deep Reinforcement Learning

Training a Deep Q Network based Agent to navigate in a virtual environment

Training an agent with deep reinforcement learning (DQN) to play a simple game in a 3D Unity environment