Learning to Update: Using Reinforcement Learning to Discover Policies for List Update
The use of machine learning models in algorithms design is a rapidly growing f ield, often termed learning-augmented algorithms. A notable advancement in this field is the use of reinforcement learning for algorithm discovery. Developing algorithms in this manner offers certain advantages, novelty a...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2024
|
| Online Access: | https://hdl.handle.net/1721.1/153854 |
| _version_ | 1811083918225440768 |
|---|---|
| author | Quaye, Isabelle A. |
| author2 | Rubinfeld, Ronitt |
| author_facet | Rubinfeld, Ronitt Quaye, Isabelle A. |
| author_sort | Quaye, Isabelle A. |
| collection | MIT |
| description | The use of machine learning models in algorithms design is a rapidly growing f ield, often termed learning-augmented algorithms. A notable advancement in this field is the use of reinforcement learning for algorithm discovery. Developing algorithms in this manner offers certain advantages, novelty and adaptability being chief among them. In this thesis, we put reinforcement learning to the task of discovering an algorithm for the list update problem. The list update problem is a classic problem with applications in caching and databases. In the process of uncovering a new list update algorithm, we also prove a competitive ratio for the transposition heuristic, which is a well-known algorithm for the list update problem. Finally, we discuss key ideas and insights from the reinforcement learning agent that hints towards optimal behavior for the list update problem. |
| first_indexed | 2024-09-23T12:41:23Z |
| format | Thesis |
| id | mit-1721.1/153854 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T12:41:23Z |
| publishDate | 2024 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1538542024-03-22T03:38:24Z Learning to Update: Using Reinforcement Learning to Discover Policies for List Update Quaye, Isabelle A. Rubinfeld, Ronitt Indyk, Piotr Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science The use of machine learning models in algorithms design is a rapidly growing f ield, often termed learning-augmented algorithms. A notable advancement in this field is the use of reinforcement learning for algorithm discovery. Developing algorithms in this manner offers certain advantages, novelty and adaptability being chief among them. In this thesis, we put reinforcement learning to the task of discovering an algorithm for the list update problem. The list update problem is a classic problem with applications in caching and databases. In the process of uncovering a new list update algorithm, we also prove a competitive ratio for the transposition heuristic, which is a well-known algorithm for the list update problem. Finally, we discuss key ideas and insights from the reinforcement learning agent that hints towards optimal behavior for the list update problem. M.Eng. 2024-03-21T19:10:50Z 2024-03-21T19:10:50Z 2024-02 2024-03-04T16:38:08.247Z Thesis https://hdl.handle.net/1721.1/153854 In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Quaye, Isabelle A. Learning to Update: Using Reinforcement Learning to Discover Policies for List Update |
| title | Learning to Update: Using Reinforcement Learning to Discover Policies for List Update |
| title_full | Learning to Update: Using Reinforcement Learning to Discover Policies for List Update |
| title_fullStr | Learning to Update: Using Reinforcement Learning to Discover Policies for List Update |
| title_full_unstemmed | Learning to Update: Using Reinforcement Learning to Discover Policies for List Update |
| title_short | Learning to Update: Using Reinforcement Learning to Discover Policies for List Update |
| title_sort | learning to update using reinforcement learning to discover policies for list update |
| url | https://hdl.handle.net/1721.1/153854 |
| work_keys_str_mv | AT quayeisabellea learningtoupdateusingreinforcementlearningtodiscoverpoliciesforlistupdate |