Deep Reinforcement Learning Behavioral Mode Switching Using Optimal Control Based on a Latent Space Objective
Abstract
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.
Cite
@article{arxiv.2406.01178,
title = {Deep Reinforcement Learning Behavioral Mode Switching Using Optimal Control Based on a Latent Space Objective},
author = {Sindre Benjamin Remman and Bjørn Andreas Kristiansen and Anastasios M. Lekkas},
journal= {arXiv preprint arXiv:2406.01178},
year = {2024}
}
Comments
Published in the proceedings of the 32nd Mediterranean Conference on Control and Automation [MED2024]