Pubblicazioni

Autori:

Castellini, A.; Bianchi, F.; Zorzi, E.; Simao, T. D.; Farinelli, A.; Spaan, M. T. J.

Titolo:

Scalable Safe Policy Improvement via Monte Carlo Tree Search

Anno:

2023

Tipologia prodotto:

Contributo in atti di convegno

Tipologia ANVUR:

Contributo in Atti di convegno

Lingua:

Inglese

Nome rivista:

PROCEEDINGS OF MACHINE LEARNING RESEARCH

ISSN Rivista:

2640-3498

Titolo del Convegno:

International Conference on Machine Learning

Luogo:

Hawaii, USA

Periodo:

23-29 July 2023

Editore:

PMLR

Casa editrice:

PMLR

Intervallo pagine:

3732-3756

Parole chiave:

Safe policy improvement, Monte Carlo Tree Search, Scalability, SPIBB

Breve descrizione dei contenuti:

Algorithms for safely improving policies are important to deploy reinforcement learning approaches in real-world scenarios. In this work, we propose an algorithm, called MCTS-SPIBB, that computes safe policy improvement online using a Monte Carlo Tree Search based strategy. We theoretically prove that the policy generated by MCTS-SPIBB converges, as the number of simulations grows, to the optimal safely improved policy generated by Safe Policy Improvement with Baseline Bootstrapping (SPIBB), a popular algorithm based on policy iteration. Moreover, our empirical analysis performed on three standard benchmark domains shows that MCTS-SPIBB scales to significantly larger problems than SPIBB because it computes the policy online and locally, i.e., only in the states actually visited by the agent.

Pagina Web:

https://proceedings.mlr.press/v202/castellini23a/castellini23a.pdf

Id prodotto:

144314

Handle IRIS:

11562/1113706

ultima modifica:

14 febbraio 2025

Citazione bibliografica:

Castellini, A.; Bianchi, F.; Zorzi, E.; Simao, T. D.; Farinelli, A.; Spaan, M. T. J., Scalable Safe Policy Improvement via Monte Carlo Tree Search in «PROCEEDINGS OF MACHINE LEARNING RESEARCH» PMLR  in Proceedings of the 40 th International Conference on Machine Learning, Honolulu, Hawaii, USA , PMLR , Atti di "International Conference on Machine Learning" , Hawaii, USA , 23-29 July 2023 , 2023 , pp. 3732-3756

Consulta la scheda completa presente nel repository istituzionale della Ricerca di Ateneo