Doing Maze using Q Learning and Value function in TD with Matlab
Budget: ₹750 – ₹1,250 INR
The project includes 2 questions where the same maze/grid problem (the shortest path to the goal has to be reached) is to be solved using Matlab with 2 methods- 1)value iteration algorithm with TD learning and 2) Q-learning algorithm .
The skeleton code for the same for both methods has been included with this.
Please use the Value function iteration with TD algorithm and Q Learning algorithm to solve the same.
Please use the skeleton code given as well.
Please show the learned state value table and the learning curves over episodes.
The skeleton code for the same for both methods has been included with this.
Please use the Value function iteration with TD algorithm and Q Learning algorithm to solve the same.
Please use the skeleton code given as well.
Please show the learned state value table and the learning curves over episodes.