SARSA Reinforcement Learning
Refer to 6.4 (Sarsa: On-Policy TD Control), Reinforcement learning: An introduction, RS Sutton, AG Barto , MIT press
In this demo, two different mazes have been solved by Reinforcement Learning technique, SARSA.
State-Action-Reward-State-Action (SARSA) is an algorithm for learning a Markov decision process policy, used in the reinforcement learning.
SARSA, Updation of Action-Value Function:
Q(S{t}, A{t}) := Q(S{t}, A{t}) + α*[ R{t+1} + γ ∗ Q(S{t+1}, A{t+1}) − Q(S{t}, A{t}) ]
Learning rate (α)
The learning rate determines to what extent the newly acquired information will override the old information. A factor of 0 will make the agent not learn anything, while a factor of 1 would make the agent consider only the most recent information.
Discount factor (γ)
The discount factor determines the importance of future rewards. A factor of 0 will make the agent "opportunistic" by only considering current rewards, while a factor approaching 1 will make it strive for a long-term high reward. If the discount factor meets or exceeds 1, the Q values may diverge.
Note: Convergence is tested on particular examples, in general convergence is not sure for above demo.
Citation pour cette source
Bhartendu (2025). SARSA Reinforcement Learning (https://www.mathworks.com/matlabcentral/fileexchange/63089-sarsa-reinforcement-learning), MATLAB Central File Exchange. Extrait(e) le .
Compatibilité avec les versions de MATLAB
Plateformes compatibles
Windows macOS LinuxCatégories
Tags
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!Découvrir Live Editor
Créez des scripts avec du code, des résultats et du texte formaté dans un même document exécutable.
Version | Publié le | Notes de version | |
---|---|---|---|
1.0.0.0 |