LePlanner: An Iterative Amortized Controller For World Models

• URL: http://arxiv.org/abs/2609.13845v1
• Date: Sat, 12 Sep 2026 10:01:21 GMT
• Title: LePlanner: An Iterative Amortized Controller For World Models
• Abstract summary: We propose LePlanner, an amortized iterative controller that learns to construct and refine latent action sequences through a frozen world-model predictor.<n>LePlanner is trained with an arrival-and-hold objective that encourages the controller to reach the goal at the earliest feasible horizon and remain there.<n>It achieves success rates of 98% on PushT, 100% on Reacher, 100% on TwoRooms, and 92% on the OGBench Cube task.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World models trained with joint-embedding predictive architectures learn compact, structured latent representations from physical interaction, yet planning in these latent spaces typically relies on one of two costly approaches. Search-based planners such as CEM, MPPI, and iCEM optimize action sequences through many predictor rollouts, achieving strong performance at the cost of high per-decision compute and latency. Policy-based methods amortize inference into a single forward pass but can degrade on contact-rich tasks where the demonstration distribution is multimodal. We propose LePlanner, an amortized iterative controller that learns to construct and refine latent action sequences through a frozen world-model predictor. LePlanner is trained with an arrival-and-hold objective that encourages the controller to reach the goal at the earliest feasible horizon and remain there. This addresses horizon-reset procrastination, a failure mode in which repeated receding-horizon replanning continually postpones goal arrival. An additional action-Gaussian loss keeps generated actions near the support of the offline dataset. Across navigation, contact-rich manipulation, and continuous-control environments, LePlanner matches or exceeds search-based planners while requiring an order of magnitude fewer predictor evaluations and 3-49x lower wall-clock time per decision. It achieves success rates of 98% on PushT, 100% on Reacher, 100% on TwoRooms, and 92% on the OGBench Cube task. These results show that much of the structure discovered through online search can be amortized into a lightweight iterative policy, enabling fast, horizon-aware, nonlinear physical control without online optimization.

Related papers

• Geometric Distributional Control: Learning Progress with Partial Structural Knowledge [6.099441855983951]
  Real-time control often sits between two limiting regimes. Predictive optimization and model-based control are powerful when dynamics, parameters, objectives, and online planning models are specified.<n> reinforcement learning can relax this requirement, but must infer long-horizon value signals from sequential data and interaction.<n>This middle regime is common in systems including autonomous driving, warehouse robotics, traffic control, and delivery drones.<n> Geometric Distributional Control (GDC) is designed for this partial-knowledge setting. It factorizes control into feasibility and progress.
  arXiv  Detail & Related papers  (2026-09-06T01:39:05Z)
• Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control [8.39933163242427]
  JEPAs learn world models by predicting in representation space rather than reconstructing pixels.<n>Prior JEPA planners often inherit ranking from embedding geometry, typically latent Euclidean distance.<n>We propose Temporal-Distance-JEPA, which retains the LeWM encoder-predictor backbone and mines a directed temporal cost from reward-free trajectories.
  arXiv  Detail & Related papers  (2026-07-28T06:38:16Z)
• PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models [50.232333672172395]
  Vision-Language-Action (VLA) models provide a unified paradigm for robotic manipulation, yet their real-world deployment is often bottlenecked by execution efficiency.<n>We propose textbfPolicyTrim, a reinforcement learning-based post-training framework that extends the reliable action chunk length and reduces redundant physical steps.<n>Our framework delivers up to a 5.83$times$ end-to-end deployment speedup without compromising task success rates.
  arXiv  Detail & Related papers  (2026-06-21T14:54:07Z)
• Latent Geometry Beyond Search: Amortizing Planning in World Models [17.571800971505787]
  We show that a learned representation can simplify control, rather than merely enabling prediction.<n>We replace iterative planning with a lightweight Goal-Conditioned Inverse Dynamics Model (GC-IDM)<n>Our controller matches or exceeds CEM in seven of eight environment-protocol settings while reducing per-decision cost by 100-130x.
  arXiv  Detail & Related papers  (2026-05-09T06:36:23Z)
• Predictive but Not Plannable: RC-aux for Latent World Models [44.63243875072762]
  Reachability-Correction auxiliary (RC-aux)<n>We present Reachability-Correction auxiliary (RC-aux), a lightweight correction for this mismatch in reconstruction-free latent world models.<n>RC-aux keeps the world-model backbone unchanged and adds planning-aligned supervision along two axes.
  arXiv  Detail & Related papers  (2026-05-08T05:43:33Z)
• Long-Horizon Manipulation via Trace-Conditioned VLA Planning [55.80061850746898]
  LoHo-Manip is a framework that scales short-horizon VLA execution to long-horizon instruction following via a dedicated task-management VLM.<n>LoHo-Manip predicts a progress-aware remaining plan that combines a subtask sequence with an explicit done + remaining split as lightweight language memory.<n>The executor VLA is adapted to condition on the rendered trace, thereby turning long-horizon decision-making into repeated local control.
  arXiv  Detail & Related papers  (2026-04-23T17:59:04Z)
• Anticipatory Planning for Multimodal AI Agents [77.62643381558613]
  We introduce TraceR1, a two-stage reinforcement learning framework that explicitly trains anticipatory reasoning.<n>TraceR1 is evaluated across seven benchmarks, covering online computer-use, offline computer-use benchmarks, and multimodal tool-use reasoning tasks.<n>Results show that anticipatory trajectory reasoning is a key principle for building multimodal agents that can reason, plan, and act effectively in complex real-world environments.
  arXiv  Detail & Related papers  (2026-03-17T16:55:11Z)
• Compositional Planning with Jumpy World Models [70.74595987225908]
  We study agents that compose pre-trained policies as temporally extended actions, enabling solutions to complex tasks that no constituent alone can solve.<n>Motivated by the geometric policy composition framework introduced in arXiv:2206.08736, we address these challenges by learning predictive models of multi-step dynamics.
  arXiv  Detail & Related papers  (2026-02-23T09:22:21Z)
• Variable Time-Step MPC for Agile Multi-Rotor UAV Interception of Dynamic Targets [6.0967385124149756]
  Agile planning using existing non-linear model predictive control methods is limited by the number of planning steps as it becomes increasingly demanding.<n>In this paper, we propose to address these limitations by introducing variable time steps and coupling them with the prediction horizon length.<n>A simplified point-mass motion primitive is used to leverage the differential flatness of quadrotor dynamics and the trajectory generation of feasible trajectories in the flat output space.
  arXiv  Detail & Related papers  (2025-03-18T11:59:24Z)
• Model-Based Reinforcement Learning via Latent-Space Collocation [110.04005442935828]
  We argue that it is easier to solve long-horizon tasks by planning sequences of states rather than just actions. We adapt the idea of collocation, which has shown good results on long-horizon tasks in optimal control literature, to the image-based setting by utilizing learned latent state space models.
  arXiv  Detail & Related papers  (2021-06-24T17:59:18Z)
• Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors [124.30562402952319]
  The ability to predict and plan into the future is fundamental for agents acting in the world. Current learning approaches for visual prediction and planning fail on long-horizon tasks. We propose a framework for visual prediction and planning that is able to overcome both of these limitations.
  arXiv  Detail & Related papers  (2020-06-23T17:58:56Z)

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.