Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications
| Autor: | Scott Niekum, Daniel S. Brown |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Generalization media_common.quotation_subject 010401 analytical chemistry Approximation algorithm Machine Learning (stat.ML) 02 engineering and technology General Medicine 01 natural sciences Machine Learning (cs.LG) 0104 chemical sciences Task (project management) Set (abstract data type) Reduction (complexity) Statistics - Machine Learning 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Function (engineering) Equivalence class Algorithm media_common |
| Zdroj: | AAAI |
| ISSN: | 2374-3468 2159-5399 |
| Popis: | Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for policy improvement and generalization. However, despite much recent interest in IRL, little work has been done to understand the minimum set of demonstrations needed to teach a specific sequential decision-making task. We formalize the problem of finding maximally informative demonstrations for IRL as a machine teaching problem where the goal is to find the minimum number of demonstrations needed to specify the reward equivalence class of the demonstrator. We extend previous work on algorithmic teaching for sequential decision-making tasks by showing a reduction to the set cover problem which enables an efficient approximation algorithm for determining the set of maximally-informative demonstrations. We apply our proposed machine teaching algorithm to two novel applications: providing a lower bound on the number of queries needed to learn a policy using active IRL and developing a novel IRL algorithm that can learn more efficiently from informative demonstrations than a standard IRL approach. In proceedings of the AAAI Conference on Artificial Intelligence, 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|