Lifelong Learning with a Changing Action Set
| Autor: | Chris Nota, Philip S. Thomas, Yash Chandak, Georgios Theocharous |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Structure (mathematical logic)
FOS: Computer and information sciences Computer Science - Machine Learning Forgetting business.industry Computer science Open problem Transition (fiction) Lifelong learning Machine Learning (stat.ML) General Medicine Space (commercial competition) Machine Learning (cs.LG) Action (philosophy) Statistics - Machine Learning Artificial intelligence business Set (psychology) |
| Zdroj: | AAAI |
| DOI: | 10.48550/arxiv.1906.01770 |
| Popis: | In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transition dynamics, changing rewards functions, etc. have been well-studied in the lifelong learning literature, the setting where the action set changes remains unaddressed. In this paper, we present an algorithm that autonomously adapts to an action set whose size changes over time. To tackle this open problem, we break it into two problems that can be solved iteratively: inferring the underlying, unknown, structure in the space of actions and optimizing a policy that leverages this structure. We demonstrate the efficiency of this approach on large-scale real-world lifelong learning problems. Comment: Thirty-fourth Conference on Artificial Intelligence (AAAI 2020) [Outstanding Student Paper Honorable Mention. ] |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|