Augmented Bayesian Policy Search - SCOOL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Augmented Bayesian Policy Search

Résumé

Deterministic policies are often preferred over stochastic ones when implemented on physical systems. They can prevent erratic and harmful behaviors while being easier to implement and interpret. However, in practice, exploration is largely performed by stochastic policies. First-order Bayesian optimization (BO) methods offer a principled way of performing exploration using deterministic policies. This is done through a learned probabilistic model of the objective function and its gradient. Nonetheless, such approaches treat policy search as a black-box problem, and thus, neglect the reinforcement learning nature of the problem. In this work, we leverage the performance difference lemma to introduce a novel mean function for the probabilistic model. This results in augmenting BO methods with the action-value function. Hence, we call our method Augmented Bayesian Search (ABS). Interestingly, this new mean function enhances the posterior gradient with the deterministic policy gradient, effectively bridging the gap between BO and policy gradient methods. The resulting algorithm combines the convenience of the direct policy search with the scalability of reinforcement learning. We validate ABS on high-dimensional locomotion problems and demonstrate competitive performance compared to existing direct policy search schemes.
Fichier principal
Vignette du fichier
3378_augmented_bayesian_policy_sear.pdf (970.16 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
licence

Dates et versions

hal-04616536 , version 1 (18-06-2024)

Licence

Identifiants

  • HAL Id : hal-04616536 , version 1

Citer

Mahdi Kallel, Debabrota Basu, Riad Akrour, Carlo d'Eramo. Augmented Bayesian Policy Search. The Twelfth International Conference on Learning Representations (ICLR), May 2024, Vienna, Austria. ⟨hal-04616536⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More