Comparing Behavioural Cloning and Reinforcement Learning for Spacecraft Guidance and Control Networks

• URL: http://arxiv.org/abs/2507.19535v1
• Date: Tue, 22 Jul 2025 07:43:38 GMT
• Title: Comparing Behavioural Cloning and Reinforcement Learning for Spacecraft Guidance and Control Networks
• Abstract summary: Guidance & control networks (G&CNETs) provide a promising alternative to on-board guidance and control (G&C) architectures for spacecraft.<n>When training G&CNETs, two predominant paradigms emerge: behavioural cloning (BC), which mimics optimal trajectories, and reinforcement learning (RL), which learns optimal behaviour through trials and errors.<n>We conduct a systematic evaluation of BC and RL specifically for training G&CNETs on continuous-thrust spacecraft trajectory optimisation tasks.<n>We introduce a novel RL training framework tailored to G&CNETs, incorporating decoupled action and control frequencies alongside reward
• Score: 4.868863044142366
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Guidance & control networks (G&CNETs) provide a promising alternative to on-board guidance and control (G&C) architectures for spacecraft, offering a differentiable, end-to-end representation of the guidance and control architecture. When training G&CNETs, two predominant paradigms emerge: behavioural cloning (BC), which mimics optimal trajectories, and reinforcement learning (RL), which learns optimal behaviour through trials and errors. Although both approaches have been adopted in G&CNET related literature, direct comparisons are notably absent. To address this, we conduct a systematic evaluation of BC and RL specifically for training G&CNETs on continuous-thrust spacecraft trajectory optimisation tasks. We introduce a novel RL training framework tailored to G&CNETs, incorporating decoupled action and control frequencies alongside reward redistribution strategies to stabilise training and to provide a fair comparison. Our results show that BC-trained G&CNETs excel at closely replicating expert policy behaviour, and thus the optimal control structure of a deterministic environment, but can be negatively constrained by the quality and coverage of the training dataset. In contrast RL-trained G&CNETs, beyond demonstrating a superior adaptability to stochastic conditions, can also discover solutions that improve upon suboptimal expert demonstrations, sometimes revealing globally optimal strategies that eluded the generation of training samples.

Related papers

• High-Precision Formation Control for Heterogeneous Multi-Robot Systems via Hierarchical Hybrid Physics-Informed Deep Reinforcement Learning [10.865402396881416]
  This paper proposes a hierarchical hybrid physics-informed deep reinforcement learning (HHy-PIDRL) framework.<n>It aims to realize high-precision, highly responsive formation control for heterogeneous multi-robot systems.<n> Experimental results demonstrate that, the success rate of both the upper-layer autonomous navigation policy network and the HM-DRL based formation control policy networks reach 100%.
  arXiv  Detail & Related papers  (2026-07-03T17:38:17Z)
• Group Sequence Policy Optimization [55.40088895148603]
  Group Sequence Policy Optimization (GSPO) is a stable, efficient, and performant reinforcement learning algorithm.<n>GSPO defines the importance ratio based on sequence likelihood and performs sequence-level clipping, rewarding, and optimization.
  arXiv  Detail & Related papers  (2025-07-24T03:50:32Z)
• Bridging Offline and Online Reinforcement Learning for LLMs [71.48552761763158]
  We investigate the effectiveness of reinforcement learning methods for finetuning large language models when transitioning from offline to semi-online.<n>Our experiments cover training on verifiable math as well as non-verifiable instruction following with a set of benchmark evaluations for both.
  arXiv  Detail & Related papers  (2025-06-26T17:25:49Z)
• Diffusion Guidance Is a Controllable Policy Improvement Operator [98.11511661904618]
  CFGRL is trained with the simplicity of supervised learning, yet can further improve on the policies in the data.<n>On offline RL tasks, we observe a reliable trend -- increased guidance weighting leads to increased performance.
  arXiv  Detail & Related papers  (2025-05-29T14:06:50Z)
• Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models [79.2162092822111]
  We systematically evaluate reinforcement learning (RL) and control-based methods on a suite of navigation tasks.<n>We employ a latent dynamics model using the Joint Embedding Predictive Architecture (JEPA) and employ it for planning.<n>Our results show that model-free RL benefits most from large amounts of high-quality data, whereas model-based planning generalizes better to unseen layouts.
  arXiv  Detail & Related papers  (2025-02-20T18:39:41Z)
• Neural-based Control for CubeSat Docking Maneuvers [0.0]
  This paper presents an innovative approach employing Artificial Neural Networks (ANN) trained through Reinforcement Learning (RL) The proposed strategy is easily implementable onboard and offers fast adaptability and robustness to disturbances by learning control policies from experience. Our findings highlight the efficacy of RL in assuring the adaptability and efficiency of spacecraft RVD, offering insights into future mission expectations.
  arXiv  Detail & Related papers  (2024-10-16T16:05:46Z)
• Gradient Boosting Reinforcement Learning [9.66275447955737]
  Gradient Boosting Reinforcement Learning (GBRL) is a framework that adapts the strengths of gradient boosting trees (GBT) to reinforcement learning (RL) tasks.<n>We show that GBRL outperforms neural networks (NNs) in domains with structured observations and categorical features.
  arXiv  Detail & Related papers  (2024-07-11T07:52:33Z)
• C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory [20.38647732528661]
  Generative Adversarial Learning (GAIL) trains a generative policy to mimic a demonstrator. It uses on-policy Imitation Reinforcement Learning (RL) to optimize a reward signal derived from a GAN-like discriminator. Recent work has shown that control theory can help with the convergence of a GAN's training.
  arXiv  Detail & Related papers  (2024-02-26T07:07:00Z)
• Learning to Sail Dynamic Networks: The MARLIN Reinforcement Learning Framework for Congestion Control in Tactical Environments [53.08686495706487]
  This paper proposes an RL framework that leverages an accurate and parallelizable emulation environment to reenact the conditions of a tactical network. We evaluate our RL learning framework by training a MARLIN agent in conditions replicating a bottleneck link transition between a Satellite Communication (SATCOM) and an UHF Wide Band (UHF) radio link.
  arXiv  Detail & Related papers  (2023-06-27T16:15:15Z)
• Controlled Descent Training [0.0]
  A novel and model-based artificial neural network (ANN) training method is developed supported by optimal control theory. The method augments training labels in order to robustly guarantee training loss convergence and improve training convergence rate. The applicability of the method is demonstrated on standard regression and classification problems.
  arXiv  Detail & Related papers  (2023-03-16T10:45:24Z)
• Offline Supervised Learning V.S. Online Direct Policy Optimization: A Comparative Study and A Unified Training Paradigm for Neural Network-Based Optimal Feedback Control [7.242569453287703]
  We first conduct a comparative study of two prevalent approaches: offline supervised learning and online direct policy optimization. Our results underscore the superiority of offline supervised learning in terms of both optimality and training time. We propose the Pre-train and Fine-tune strategy as a unified training paradigm for optimal feedback control.
  arXiv  Detail & Related papers  (2022-11-29T05:07:13Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)
• Reinforcement Learning for Low-Thrust Trajectory Design of Interplanetary Missions [77.34726150561087]
  This paper investigates the use of reinforcement learning for the robust design of interplanetary trajectories in presence of severe disturbances. An open-source implementation of the state-of-the-art algorithm Proximal Policy Optimization is adopted. The resulting Guidance and Control Network provides both a robust nominal trajectory and the associated closed-loop guidance law.
  arXiv  Detail & Related papers  (2020-08-19T15:22:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.