/Reinforcement-Learning--Obstacle-Aware-Planning

This repository contains an implementation of Proximal Policy Optimization (PPO) using StableBaselines 3 to push an object to it goal state in presence of obstacles.

Primary LanguageJupyter Notebook

Introduction

  • Here is a PPO implementation to push an object to its goal location using model-free RL.
  • I am still updating the README with more facts and figures, as I run more experiments on this.
  • Stay tuned for more exciting results and conclusions.

Result

  • Here is a short video showing the result of pushing the block in presence of obstacle.

image Watch the video