Zero-shot Imitation Learning by Latent Topology Mapping

arXiv 2605.08450 ↗First posted 8 May 2026cs.LG cs.AIcited by 1

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 43 of its 58 references that are in the map. First posted on arXiv 8 May 2026.

Builds on

43 of 58 references.

References · 43

2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
2016Generative Adversarial Imitation Learningcited by 1,576
2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,245
2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,227
2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
2019When Does Label Smoothing Help?cited by 985

31 more

2019Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reductioncited by 833
2018Recurrent World Models Facilitate Policy Evolutioncited by 761
2019Behavior Regularized Offline Reinforcement Learningcited by 654
2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 636
2020MOPO: Model-based Offline Policy Optimizationcited by 630
2020MOReL : Model-Based Offline Reinforcement Learningcited by 582
2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
2018An Algorithmic Perspective on Imitation Learningcited by 455
2018Data-Efficient Hierarchical Reinforcement Learningcited by 436
2016The Option-Critic Architecturecited by 433
2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
2016Learning to reinforcement learncited by 369
2021COMBO: Conservative Offline Model-Based Policy Optimizationcited by 365
2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 328
2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 320
2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 282
2020Critic Regularized Regressioncited by 269
2022A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problemscited by 228
2019Search on the Replay Buffer: Bridging Planning and Reinforcement Learningcited by 188
2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 184
2022Model-Based Imitation Learning for Urban Drivingcited by 149
2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 145
2018Variational Option Discovery Algorithmscited by 121
2019BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learningcited by 90
2018Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddingscited by 52
2022Skill-based Model-based Reinforcement Learningcited by 50
2021MobILE: Model-Based Imitation Learning From Observation Alonecited by 44
2018Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependenciescited by 43
2019DAC: The Double Actor-Critic Architecture for Learning Optionscited by 43
2022Hierarchical Model-Based Imitation Learning for Planning in Autonomous Drivingcited by 43
2021CARL: A Benchmark for Contextual and Adaptive Reinforcement Learningcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

2026Missing Bridges: Composition-Aware Active Imitation Learningcited by 0

Similar, not cited

Close in wording, no citation either way