Multi agent PPO implementation in Pytorch for Unity ML Agents environments.

Controlling a 7 DOF manipulator from the panda gym reacher environment using DDPG

Controlling a double-jointed arm to reach target locations with Deep Deterministic Policy Gradients (DDPG)

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

Deep Reinforcement Learning: Continuous Control. Solve the Unity ML-Agents Reacher Environment.

Using DDPG to solve the Reacher environment (Udacity project)

DDPG algorithm applied for the double-jointed arm that can move to target locations.

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

An implementation of DDPG agent to solve a Unity environment like Reacher and Crawler.

This repository trains independent multiple identical agents in Reacher Unity Environment.

Reinforcement Learning Project using DDPG