Optimal-Path-Planning-Deep-Reinforcement-Learning
Optimal-Path-Planning-Deep-Reinforcement-Learning copied to clipboard
Optimal Path Planning with Deep Reinforcement Learning
Optimal Path Planning: Deep Reinforcement Learning
Optimal Path Planning with Deep Reinforcement Learning
Basic concepts of Q learning algorithm, markov Decision Processes, Temporal Difference, and Deep Q Networks are used to train a tiny car find the optimal path from top left corner to bottom right corner.
![](https://github.com/naderAsadi/Optimal-Path-Planning-Deep-Reinforcement-Learning/blob/master/output.jpg)