Related papers: Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architectures

Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architectures

URL: http://arxiv.org/abs/2602.15533v1
Date: Tue, 17 Feb 2026 12:31:53 GMT
Title: Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architectures
Abstract summary: We develop a library-based scheme that enables effective knowledge transfer across multirotor configurations.<n>We demonstrate that our scheme saves on average up to $73.5%$ of environment interactions (compared to training a policy from scratch) across diverse quadrotor and hexarotor designs.
Score: 11.449763494464053
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Efficiently training control policies for robots is a major challenge that can greatly benefit from utilizing knowledge gained from training similar systems through cross-embodiment knowledge transfer. In this work, we focus on accelerating policy training using a library-based initialization scheme that enables effective knowledge transfer across multirotor configurations. By leveraging a physics-aware neural control architecture that combines a reinforcement learning-based controller and a supervised control allocation network, we enable the reuse of previously trained policies. To this end, we utilize a policy evaluation-based similarity measure that identifies suitable policies for initialization from a library. We demonstrate that this measure correlates with the reduction in environment interactions needed to reach target performance and is therefore suited for initialization. Extensive simulation and real-world experiments confirm that our control architecture achieves state-of-the-art control performance, and that our initialization scheme saves on average up to $73.5\%$ of environment interactions (compared to training a policy from scratch) across diverse quadrotor and hexarotor designs, paving the way for efficient cross-embodiment transfer in reinforcement learning.

Related papers

PCHC: Enabling Preference Conditioned Humanoid Control via Multi-Objective Reinforcement Learning [50.63196995993855]
We propose a novel framework leveraging Multi-Objective Reinforcement Learning (MORL) to achieve Preference-Conditioned Humanoid Control (PCHC)<n>Our framework enables a single, preference-conditioned policy to exhibit a wide spectrum of diverse behaviors.
arXiv Detail & Related papers (2026-03-25T07:55:37Z)
Decentralized Learning Strategies for Estimation Error Minimization with Graph Neural Networks [86.99017195607077]
We address real-time sampling and estimation of autoregressive Markovian sources in wireless networks.<n>We propose a graphical reinforcement learning framework for policy optimization.<n>Theoretically, our proposed policies are transferable, allowing a policy trained on one graph to be effectively applied to structurally similar graphs.
arXiv Detail & Related papers (2026-01-19T02:18:45Z)
Transfer learning strategies for accelerating reinforcement-learning-based flow control [0.0]
This work investigates transfer learning strategies to accelerate deep reinforcement learning (DRL) for multifidelity control of chaotic fluid flows.<n> Progressive neural networks (PNNs) are employed for the first time in the context of DRL-based flow control.<n>PNNs enable stable and efficient transfer by preserving prior knowledge and providing consistent performance gains.
arXiv Detail & Related papers (2025-10-15T09:52:06Z)
Pretraining in Actor-Critic Reinforcement Learning for Robot Motion Control [6.288719574558261]
This work aims to define a paradigm for pretraining neural network models.<n>We use a task-agnostic exploration-based data collection algorithm to gather diverse, dynamic transition data.<n>The pretrained weights are loaded into both the actor and critic networks to warm-start the policy optimization of actual tasks.
arXiv Detail & Related papers (2025-10-14T10:25:40Z)
A Fast Initialization Method for Neural Network Controllers: A Case Study of Image-based Visual Servoing Control for the multicopter Interception [5.006133776992552]
Reinforcement learning-based controller design methods often require substantial data in the initial training phase.<n>A stable neural network controller can not only serve as an initial policy for reinforcement learning, but also act as an initial state for learning-based Lyapunov control methods.
arXiv Detail & Related papers (2025-09-23T14:56:59Z)
In-Context Learning for Gradient-Free Receiver Adaptation: Principles, Applications, and Theory [54.92893355284945]
Deep learning-based wireless receivers offer the potential to dynamically adapt to varying channel environments.<n>Current adaptation strategies, including joint training, hypernetwork-based methods, and meta-learning, either demonstrate limited flexibility or necessitate explicit optimization through gradient descent.<n>This paper presents gradient-free adaptation techniques rooted in the emerging paradigm of in-context learning (ICL)
arXiv Detail & Related papers (2025-06-18T06:43:55Z)
ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characters [28.446959320429656]
We introduce ControlVAE, a model-based framework for learning generative motion control policies based on variational autoencoders (VAE) Our framework can learn a rich and flexible latent representation of skills and a skill-conditioned generative control policy from a diverse set of unorganized motion sequences. We demonstrate the effectiveness of ControlVAE using a diverse set of tasks, which allows realistic and interactive control of the simulated characters.
arXiv Detail & Related papers (2022-10-12T10:11:36Z)
Towards Task-Prioritized Policy Composition [10.477909792349823]
We propose a novel task-prioritized composition framework for Reinforcement Learning. Our framework has the potential to facilitate knowledge transfer and modular design while greatly increasing data efficiency and data reuse for Reinforcement Learning agents. Unlike null-space control, our approach allows learning globally optimal policies for the compound task by online learning in the indifference-space of higher-level policies after initial compound policy construction.
arXiv Detail & Related papers (2022-09-20T08:08:04Z)
Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
arXiv Detail & Related papers (2022-06-07T13:51:35Z)
A Regularized Implicit Policy for Offline Reinforcement Learning [54.7427227775581]
offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. We propose a framework that supports learning a flexible yet well-regularized fully-implicit policy. Experiments and ablation study on the D4RL dataset validate our framework and the effectiveness of our algorithmic designs.
arXiv Detail & Related papers (2022-02-19T20:22:04Z)
Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion [95.1825179206694]
We present a framework that synthesizes robust controllers for a quadruped robot. A high-level controller learns to choose from a set of primitives in response to changes in the environment. A low-level controller that utilizes an established control method to robustly execute the primitives.
arXiv Detail & Related papers (2020-09-21T16:49:26Z)

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