mlsanityData to 14 Oct 2026

GCImOpt: Learning efficient goal-conditioned policies by imitating optimal trajectories

arXiv 2604.22724 ↗First posted 24 Apr 2026cs.RO cs.SY eess.SYcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

also in 1 more
Abstract (arXiv)

Imitation learning is a well-established approach for machine-learning-based control. However, its applicability depends on having access to demonstrations, which are often expensive to collect and/or suboptimal for solving the task. In this work, we present GCImOpt, an approach to learn efficient goal-conditioned policies by training on datasets generated by trajectory optimization. Our approach for dataset generation is computationally efficient, can generate thousands of optimal trajectories in minutes on a laptop computer, and produces high-quality demonstrations. Further, by means of a data augmentation scheme that treats intermediate states as goals, we are able to increase the training dataset size by an order of magnitude. Using our generated datasets, we train goal-conditioned neural network policies that can control the system towards arbitrary goals. To demonstrate the generality of our approach, we generate datasets and then train policies for various control tasks, namely cart-pole stabilization, planar and three-dimensional quadcopter stabilization, and point reaching using a 6-DoF robot arm. We show that our trained policies can achieve high success rates and near-optimal control profiles, all while being small (less than 80,000 neural network parameters) and fast enough (up to more than 6,000 times faster than a trajectory optimization solver) that they could be deployed onboard resource-constrained controllers. We provide videos, code, datasets and pre-trained policies under a free software license; see our project website https://jongoiko.github.io/gcimopt/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 17 of its 38 references that are in the map. First posted on arXiv 24 Apr 2026.

Builds on

17 of 38 references.

Closest ancestors · 2

Same direction, newest first

  1. 2019Goal-conditioned Imitation Learning13 Jun
  2. 2019Learning the optimal state-feedback via supervised imitation learning7 Jan

Other references · 15

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  2. 2017End-to-end Driving via Conditional Imitation Learningcited by 485
  3. 2019Learning Latent Plans from Playcited by 316
  4. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 236
  5. 2022GNM: A General Navigation Model to Drive Any Robotcited by 171
  6. 2017Searching for Activation Functionscited by 169
  7. 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 158
  8. 2021Equinox: neural networks in JAX via callable PyTrees and filtered transformationscited by 148
  9. 2021safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Roboticscited by 50
  10. 2016Real-time optimal control via Deep Neural Networks: study on landing problemscited by 28
  11. 2016PLATO: Policy Learning using Adaptive Trajectory Optimizationcited by 24
  12. 2023End-to-end Neural Network Based Quadcopter controlcited by 11
3 more
  1. 2017Combining Trajectory Optimization, Supervised Machine Learning, and Model Structure for Mitigating the Curse of Dimensionality in the Control of Bipedal Robotscited by 5
  2. 2023FATROP : A Fast Constrained Optimal Control Problem Solver for Robot Trajectory Optimization and Controlcited by 5
  3. 2019Learning Dynamic-Objective Policies from a Class of Optimal Trajectoriescited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
  2. 2022GoalsEye: Learning High Speed Precision Table Tennis on a Physical Robot
  3. 2021Imitation Learning via Simultaneous Optimization of Policies and Auxiliary Trajectories
  4. 2019MPC-Net: A First Principles Guided Policy Search
  5. 2022Output Feedback Tube MPC-Guided Data Augmentation for Robust, Efficient Sensorimotor Policy Learning
  6. 2019Learning to Reach Goals via Iterated Supervised Learning
  7. 2025Robust Offline Imitation Learning Through State-level Trajectory Stitching
  8. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning