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

Implementation of project 3 for Udacity's Deep Reinforcement Learning Nanodegree

An implementation of MADDPG multi-agent to solve a Unity environment like Tennis and Soccer.

An unofficial library for interacting with Discord Webhook aimed at use in the Unity environment

Implementation of project 2 for Udacity's Deep Reinforcement Learning Nanodegree

Deep Reinforcement Learning Projects

We train an agent to manuver in a 3-D environment avoiding blue bananas and picking yellow ones as fast as possible.

Implementation of project 1 for Udacity's Deep Reinforcement Learning Nanodegree

This is the 2nd project in Udacity DRLND, which is practice for training an agent that controls a robotic arm in Unity's Reacher environment using the Deep Deterministic Policy Gradients (DDPG) algorithm.

Create and train a double-jointed arm agent that is able to maintain its hand in contact with a moving target

Multiagent RL

Collaboration and Competition (using multi agent reinforcement learning). Train a pair of agents to play tennis.

Training an agent to perform continuous task

Solving Reacher environment using deep reinforcement learning

Train double-jointed arms to reach target locations using Proximal Policy Optimization (PPO) in Pytorch

Deep reinforcement Learning Nanodegree - Navigation Project

Solution of a first project of the deep reinforcement learning nanodegree at Udacity.

An implementation of Deep Q-Learning Network for solving a Unity environment that can navigate and collect bananas in a large, square world.