Maze Solver (Reinforcement Learning)

Maze Solving using Value iterations, Dynamic Programming
818 download
Aggiornato 22 mag 2017

Visualizza la licenza

Refer to 4.1, Reinforcement learning: An introduction, RS Sutton, AG Barto , MIT press
Value Iterations:
Algorithms of dynamic programming to solve finite MDPs. Policy evaluation refers to the (typically) iterative computation of the value functions for a given policy. Policy improvement refers to the computation of an improved policy given the value function for that policy. Putting these two computations together, we obtain policy iteration and value iteration, the two most popular DP methods. Either of these can be used to reliably compute optimal policies and value functions for finite MDPs given complete knowledge of the MDP.

◮ Problem: find optimal policy π
◮ Solution: iterative application of Bellman optimality backup
◮ v1 → v2 → ... → v∗
◮ Using synchronous backups, At each iteration k + 1 For all states s ∈ S : Update v_{k+1}(s) from v_{k}(s')
◮ Convergence to v∗ will be proven later
◮ Unlike policy iteration, there is no explicit policy
◮ Intermediate value functions may not correspond to any policy

Cita come

Bhartendu (2024). Maze Solver (Reinforcement Learning) (https://www.mathworks.com/matlabcentral/fileexchange/63062-maze-solver-reinforcement-learning), MATLAB Central File Exchange. Recuperato .

Compatibilità della release di MATLAB
Creato con R2016a
Compatibile con qualsiasi release
Compatibilità della piattaforma
Windows macOS Linux
Categorie
Scopri di più su Labyrinth problems in Help Center e MATLAB Answers

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Versione Pubblicato Note della release
1.0.0.0