Catalogo dei prodotti della ricerca
IRIS è la soluzione IT che facilita la raccolta e la gestione dei dati relativi alle attività e ai prodotti della ricerca. Fornisce a ricercatori, amministratori e valutatori gli strumenti per monitorare i risultati della ricerca, aumentarne la visibilità e allocare in modo efficace le risorse disponibili.
EnglishA common problem in Reinforcement Learning (RL) is that the reward function is hard to express. This can be overcome by resorting to Inverse Reinforcement Learning (IRL), which consists in first obtaining a reward function from a set of execution traces generated by the expert agent, and then making the learning agent learn the expert's behavior --this is known as Transfer Learning (TL). Typical IRL solutions rely on a numerical representation of the reward function, which raises problems related to the adopted optimization procedures. We describe a TL method where the execution traces generated by the expert agent, possibly via planning, are used to produce a logical (as opposed to numerical) specification of the reward function, to be incorporated in a device known as Restraining Bolt (RB). The RB can be attached to the learning agent to drive the learning process and ultimately make it imitate the expert. We show that TL can be applied to heterogeneous agents, with the expert, the learner and the RB using different representations of the environment's actions and states, without specifying mappings among their representations.
Imitation Learning over Heterogeneous Agents with Restraining Bolts / De Giacomo, Giuseppe; Iocchi, Luca; Favorito, Marco; Patrizi, Fabio. - 30(2020), pp. 517-521. ((Intervento presentato al convegno 30th International Conference on Automated Planning and Scheduling, ICAPS 2020 tenutosi a Nancy; France.
| Titolo: | Imitation Learning over Heterogeneous Agents with Restraining Bolts | |
| Autori: | ||
| Data di pubblicazione: | 2020 | |
| Serie: | ||
| Citazione: | Imitation Learning over Heterogeneous Agents with Restraining Bolts / De Giacomo, Giuseppe; Iocchi, Luca; Favorito, Marco; Patrizi, Fabio. - 30(2020), pp. 517-521. ((Intervento presentato al convegno 30th International Conference on Automated Planning and Scheduling, ICAPS 2020 tenutosi a Nancy; France. | |
| Handle: | http://hdl.handle.net/11573/1434370 | |
| Appartiene alla tipologia: | 04b Atto di convegno in volume |
File allegati a questo prodotto
| File | Note | Tipologia | Licenza | |
|---|---|---|---|---|
| DeGiacomo_Imitation-Learning_2020.pdf | Versione editoriale (versione pubblicata con il layout dell'editore) | Tutti i diritti riservati (All rights reserved) | Administrator Richiedi una copia |
Copyright © 2022