Enregistré dans:
Détails bibliographiques
Auteurs principaux: Remman, Sindre Benjamin, Kristiansen, Bjørn Andreas, Lekkas, Anastasios M.
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2406.01178
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909216560644096
author Remman, Sindre Benjamin
Kristiansen, Bjørn Andreas
Lekkas, Anastasios M.
author_facet Remman, Sindre Benjamin
Kristiansen, Bjørn Andreas
Lekkas, Anastasios M.
contents In this work, we use optimal control to change the behavior of a deep reinforcement learning policy by optimizing directly in the policy's latent space. We hypothesize that distinct behavioral patterns, termed behavioral modes, can be identified within certain regions of a deep reinforcement learning policy's latent space, meaning that specific actions or strategies are preferred within these regions. We identify these behavioral modes using latent space dimension-reduction with \ac*{pacmap}. Using the actions generated by the optimal control procedure, we move the system from one behavioral mode to another. We subsequently utilize these actions as a filter for interpreting the neural network policy. The results show that this approach can impose desired behavioral modes in the policy, demonstrated by showing how a failed episode can be made successful and vice versa using the lunar lander reinforcement learning environment.
format Preprint
id arxiv_https___arxiv_org_abs_2406_01178
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Reinforcement Learning Behavioral Mode Switching Using Optimal Control Based on a Latent Space Objective
Remman, Sindre Benjamin
Kristiansen, Bjørn Andreas
Lekkas, Anastasios M.
Machine Learning
Systems and Control
In this work, we use optimal control to change the behavior of a deep reinforcement learning policy by optimizing directly in the policy's latent space. We hypothesize that distinct behavioral patterns, termed behavioral modes, can be identified within certain regions of a deep reinforcement learning policy's latent space, meaning that specific actions or strategies are preferred within these regions. We identify these behavioral modes using latent space dimension-reduction with \ac*{pacmap}. Using the actions generated by the optimal control procedure, we move the system from one behavioral mode to another. We subsequently utilize these actions as a filter for interpreting the neural network policy. The results show that this approach can impose desired behavioral modes in the policy, demonstrated by showing how a failed episode can be made successful and vice versa using the lunar lander reinforcement learning environment.
title Deep Reinforcement Learning Behavioral Mode Switching Using Optimal Control Based on a Latent Space Objective
topic Machine Learning
Systems and Control
url https://arxiv.org/abs/2406.01178