This paper discusses how Q-Learning and Deep Q-Networks (DQN) canbe applied to state-action problems described by a Markov decision process(MDP). These are machine learning methods for finding the optimal choiceof action at each time step, resulting in the optimal policy. The limitationsand advantages for the two methods are discussed, with the main limitationbeing the fact that Q-learning is unable to be used on problems with infinitestate spaces. Q-learning, however, has an advantage in the simplicity of thealgorithm, leading to a better understanding of what the algorithm is actuallydoing. Q-Learning did manage to find the optimal policy for the simpleproblem studied in this paper, but was unable to do so for the advancedproblem. The Deep Q-Network (DQN) approach was able to solve bothproblems, with a drawback in it being harder to understand what the algorithmactually is doing.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:kth-348638 |
| Date | January 2024 |
| Creators | Blizzard, Christopher, Wiktorsson, Emil |
| Publisher | KTH, Skolan för teknikvetenskap (SCI) |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | TRITA-SCI-GRU ; 2024:247 |
Page generated in 0.0076 seconds