Continuous Action Reinforcement Learning From a Mixture of Interpretable Experts

Riad Akrour*, Davide Tateo, Jan Peters

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: LehtiartikkeliArticleScientificvertaisarvioitu

1 Sitaatiot (Scopus)

Abstrakti

Reinforcement learning (RL) has demonstrated its ability to solve high dimensional tasks by leveraging non-linear function approximators. However, these successes are mostly achieved by 'black-box' policies in simulated domains. When deploying RL to the real world, several concerns regarding the use of a 'black-box' policy might be raised. In order to make the learned policies more transparent, we propose in this paper a policy iteration scheme that retains a complex function approximator for its internal value predictions but constrains the policy to have a concise, hierarchical, and human-readable structure, based on a mixture of interpretable experts. Each expert selects a primitive action according to a distance to a prototypical state. A key design decision to keep such experts interpretable is to select the prototypical states from trajectory data. The main technical contribution of the paper is to address the challenges introduced by this non-differentiable prototypical state selection procedure. Experimentally, we show that our proposed algorithm can learn compelling policies on continuous action deep RL benchmarks, matching the performance of neural network based policies, but returning policies that are more amenable to human inspection than neural network or linear-in-feature policies.

AlkuperäiskieliEnglanti
Sivut6795-6806
Sivumäärä12
JulkaisuIEEE Transactions on Pattern Analysis and Machine Intelligence
Vuosikerta44
Numero10
DOI - pysyväislinkit
TilaJulkaistu - 1 lokak. 2022
OKM-julkaisutyyppiA1 Julkaistu artikkeli, soviteltu

Sormenjälki

Sukella tutkimusaiheisiin 'Continuous Action Reinforcement Learning From a Mixture of Interpretable Experts'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä