Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kernbach, Andreas, Elsheikh, Amr, Grupp, Nicolas, Nagel, René, Huber, Marco F.
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2602.23804
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910034915491840
author Kernbach, Andreas
Elsheikh, Amr
Grupp, Nicolas
Nagel, René
Huber, Marco F.
author_facet Kernbach, Andreas
Elsheikh, Amr
Grupp, Nicolas
Nagel, René
Huber, Marco F.
contents Reinforcement learning (RL) actor-critic algorithms enable autonomous learning but often require a large number of environment interactions, which limits their applicability in robotics. Leveraging expert data can reduce the number of required environment interactions. A common approach is actor pretraining, where the actor network is initialized via behavioral cloning on expert demonstrations and subsequently fine-tuned with RL. In contrast, the initialization of the critic network has received little attention, despite its central role in policy optimization. This paper proposes a pretraining approach for actor-critic algorithms like Proximal Policy Optimization (PPO) that uses expert demonstrations to initialize both networks. The actor is pretrained via behavioral cloning, while the critic is pretrained using returns obtained from rollouts of the pretrained policy. The approach is evaluated on 15 simulated robotic manipulation and locomotion tasks. Experimental results show that actor-critic pretraining improves sample efficiency by 86.1% on average compared to no pretraining and by 30.9% to actor-only pretraining.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23804
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Actor-Critic Pretraining for Proximal Policy Optimization
Kernbach, Andreas
Elsheikh, Amr
Grupp, Nicolas
Nagel, René
Huber, Marco F.
Machine Learning
Reinforcement learning (RL) actor-critic algorithms enable autonomous learning but often require a large number of environment interactions, which limits their applicability in robotics. Leveraging expert data can reduce the number of required environment interactions. A common approach is actor pretraining, where the actor network is initialized via behavioral cloning on expert demonstrations and subsequently fine-tuned with RL. In contrast, the initialization of the critic network has received little attention, despite its central role in policy optimization. This paper proposes a pretraining approach for actor-critic algorithms like Proximal Policy Optimization (PPO) that uses expert demonstrations to initialize both networks. The actor is pretrained via behavioral cloning, while the critic is pretrained using returns obtained from rollouts of the pretrained policy. The approach is evaluated on 15 simulated robotic manipulation and locomotion tasks. Experimental results show that actor-critic pretraining improves sample efficiency by 86.1% on average compared to no pretraining and by 30.9% to actor-only pretraining.
title Actor-Critic Pretraining for Proximal Policy Optimization
topic Machine Learning
url https://arxiv.org/abs/2602.23804