Minimax-Regret Querying on Side Effects for Safe Optimality in Factored Markov Decision Processes
| Autor: | Shun Zhang, Edmund H. Durfee, Satinder Singh |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Mathematical optimization
Computer science 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Regret 02 engineering and technology Markov decision process 010501 environmental sciences 01 natural sciences 0105 earth and related environmental sciences |
| Zdroj: | IJCAI |
| DOI: | 10.24963/ijcai.2018/676 |
| Popis: | As it achieves a goal on behalf of its human user, an autonomous agent's actions may have side effects that change features of its environment in ways that negatively surprise its user. An agent that can be trusted to operate safely should thus only change features the user has explicitly permitted. We formalize this problem, and develop a planning algorithm that avoids potentially negative side effects given what the agent knows about (un)changeable features. Further, we formulate a provably minimax-regret querying strategy for the agent to selectively ask the user about features that it hasn't explicitly been told about. We empirically show how much faster it is than a more exhaustive approach and how much better its queries are than those found by the best known heuristic. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|