Zero-shot Imitation Learning by Latent Topology Mapping

• URL: http://arxiv.org/abs/2605.08450v1
• Date: Fri, 08 May 2026 20:16:52 GMT
• Title: Zero-shot Imitation Learning by Latent Topology Mapping
• Abstract summary: We study the long-horizon, goal-conditioned setting where a fixed demonstration dataset contains useful behavior, but not complete examples for every task the agent must solve.<n>Existing imitation learning methods can learn strong policies from demonstrations, but when solving long-horizon tasks, small errors accumulate over long primitive-action trajectories and make zero-shot adaptation to new tasks unreliable.<n>We introduce Zero-shot Agents from Latent Topologies (ZALT), an imitation-learning method that solves unseen start-goal tasks beyond those demonstrated during training.
• Score: 18.335598046913418
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Imitation learning is effective for training agents when expert demonstrations are available, but collecting demonstrations for every complex task in an environment is costly. We study the long-horizon, goal-conditioned setting where a fixed demonstration dataset contains useful behavior, but not complete examples for every task the agent must solve. Existing imitation learning methods can learn strong policies from demonstrations, but when solving long-horizon tasks, small errors accumulate over long primitive-action trajectories and make zero-shot adaptation to new tasks unreliable. We introduce Zero-shot Agents from Latent Topologies (ZALT), an imitation-learning method that solves unseen start-goal tasks beyond those demonstrated during training. ZALT identifies latent hub states where trajectories converge or diverge, learns policies and a dynamics model over hub-to-hub transitions, and plans over the hub topology to complete new tasks. This topology makes demonstrated behaviors explicitly composable while compressing long tasks into shorter sequences of abstract transitions -- combined, these enable ZALT to perform zero-shot adaptation. In a complex 3D maze environment, ZALT achieves 55% zero-shot success on unseen tasks, compared to 6% for the strongest baseline.

Related papers

• Learning from Demonstrations via Capability-Aware Goal Sampling [12.442790487354742]
  Cago is a learning-from-demonstrations method that mitigates the brittle dependence on expert trajectories for direct imitation.<n>We show that Cago significantly improves sample efficiency and final performance across a range of sparse-reward, goal-conditioned tasks.
  arXiv  Detail & Related papers  (2026-01-13T17:03:31Z)
• EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models [57.75717492488268]
  Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models.<n>Supervised Finetuning (SFT) requires hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training.<n>We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations.
  arXiv  Detail & Related papers  (2025-12-16T18:26:38Z)
• Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models [71.34520793462069]
  Unsupervised reinforcement learning (RL) aims at pre-training agents that can solve a wide range of downstream tasks in complex environments.<n>We introduce a novel algorithm regularizing unsupervised RL towards imitating trajectories from unlabeled behavior datasets.<n>We demonstrate the effectiveness of this new approach in a challenging humanoid control problem.
  arXiv  Detail & Related papers  (2025-04-15T10:41:11Z)
• GenPlan: Generative Sequence Models as Adaptive Planners [0.0]
  Sequence models have demonstrated remarkable success in behavioral planning by leveraging previously collected demonstrations.<n>However, solving multi-task missions remains a significant challenge, particularly when the planner must adapt to unseen constraints and tasks.<n>We propose GenPlan: a discrete-flow model for adaptive planner, enabling sample-generative exploration and exploitation.
  arXiv  Detail & Related papers  (2024-12-11T17:32:33Z)
• Adaptformer: Sequence models as adaptive iterative planners [0.0]
  Decision-making in multi-task missions is a challenging problem for autonomous systems.<n>We propose Adaptformer, an adaptive planner that utilizes sequence models for sample-efficient exploration and exploitation.<n>We show that Adaptformer outperforms the state-of-the-art method by up to 25% in multi-goal maze reachability tasks.
  arXiv  Detail & Related papers  (2024-11-30T00:34:41Z)
• Semi-Supervised One-Shot Imitation Learning [83.94646047695412]
  One-shot Imitation Learning aims to imbue AI agents with the ability to learn a new task from a single demonstration. We introduce the semi-supervised OSIL problem setting, where the learning agent is presented with a large dataset of trajectories. We develop an algorithm specifically applicable to this semi-supervised OSIL setting.
  arXiv  Detail & Related papers  (2024-08-09T18:11:26Z)
• GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation [1.4703485217797363]
  GO-DICE is an offline IL technique for goal-conditioned long-horizon sequential tasks. Inspired by the expansive DICE-family of techniques, policy learning at both the levels transpires within the space of stationary distributions. Experimental results substantiate that GO-DICE outperforms recent baselines.
  arXiv  Detail & Related papers  (2023-12-17T19:47:49Z)
• Task-Distributionally Robust Data-Free Meta-Learning [99.56612787882334]
  Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data. For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift ( TDS) and Task-Distribution Corruption (TDC)
  arXiv  Detail & Related papers  (2023-11-23T15:46:54Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning [59.08197876733052]
  Auxiliary-Task Learning (ATL) aims to improve the performance of the target task by leveraging the knowledge obtained from related tasks. Sometimes, learning multiple tasks simultaneously results in lower accuracy than learning only the target task, known as negative transfer. ForkMerge is a novel approach that periodically forks the model into multiple branches, automatically searches the varying task weights.
  arXiv  Detail & Related papers  (2023-01-30T02:27:02Z)
• Skill-based Meta-Reinforcement Learning [65.31995608339962]
  We devise a method that enables meta-learning on long-horizon, sparse-reward tasks. Our core idea is to leverage prior experience extracted from offline datasets during meta-learning.
  arXiv  Detail & Related papers  (2022-04-25T17:58:19Z)
• Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation [14.901636098553848]
  Solving tasks with a sparse reward in a sample-efficient manner poses a challenge to modern reinforcement learning. Existing strategies explore based on task-agnostic goal distributions, which can render the solution of long-horizon tasks impractical. We extend hindsight relabelling mechanisms to guide exploration along task-specific distributions implied by a small set of successful demonstrations.
  arXiv  Detail & Related papers  (2021-12-01T16:12:32Z)

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.