Learning Lifted Action Models from Unsupervised Visual Traces

• URL: http://arxiv.org/abs/2604.19043v1
• Date: Tue, 21 Apr 2026 03:49:04 GMT
• Title: Learning Lifted Action Models from Unsupervised Visual Traces
• Abstract summary: We propose a deep learning framework that jointly learns state prediction, action prediction, and a lifted action model.<n>We also introduce a mixed-integer linear program (MILP) to prevent prediction collapse and self-reinforcing errors.<n>Experiments across multiple domains show that integrating MILP-based correction helps the model escape local optima and converge toward globally consistent solutions.
• Score: 38.479081137300945
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Efficient construction of models capturing the preconditions and effects of actions is essential for applying AI planning in real-world domains. Extensive prior work has explored learning such models from high-level descriptions of state and/or action sequences. In this paper, we tackle a more challenging setting: learning lifted action models from sequences of state images, without action observation. We propose a deep learning framework that jointly learns state prediction, action prediction, and a lifted action model. We also introduce a mixed-integer linear program (MILP) to prevent prediction collapse and self-reinforcing errors among predictions. The MILP takes the predicted states, actions, and action model over a subset of traces and solves for logically consistent states, actions, and action model that are as close as possible to the original predictions. Pseudo-labels extracted from the MILP solution are then used to guide further training. Experiments across multiple domains show that integrating MILP-based correction helps the model escape local optima and converge toward globally consistent solutions.

Related papers

• CAER: Causal Action Effect Reweighting for World Model Training [31.737118584204342]
  We introduce Causal Action Effect Reweighting (CAER), a training paradigm that redistributes supervision toward the tokens whose predicted future is causally affected by the action.<n>CAER contrasts the model's own predictions with and without action conditioning to localize these tokens online, then normalizes the resulting effect map into a weight that preserves the total coefficient mass and changes only where it is spent.<n> Experiments across heterogeneous action-conditioned world-model tasks show that CAER converges to better solutions than uniform MSE training, with consistent improvements in the physical consistency, controllability, and visual quality of generated videos
  arXiv  Detail & Related papers  (2026-08-31T14:49:56Z)
• Self-Evolving World Models for LLM Agent Planning [72.99782619992361]
  We introduce WorldEvolver, a self-evolving world model framework that revises its deployment-time context while keeping the downstream agent and all model parameters frozen.<n>WorldEvolver achieves the highest prediction accuracy across three backbones and leads other world model baselines on downstream agent success rate.
  arXiv  Detail & Related papers  (2026-06-29T17:58:43Z)
• Feedback World Model Enables Precise Guidance of Diffusion Policy [36.965417653906535]
  We propose feedback world model, a new paradigm that closes the loop between prediction and observation at inference time.<n>We show that our method substantially improves both prediction accuracy and policy performance under distribution shift.<n>In particular, it reduces world model prediction error by up to 76.4% and improves out-of-distribution (OOD) success rate by 30%.
  arXiv  Detail & Related papers  (2026-05-15T07:52:13Z)
• HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models [58.191567345416836]
  World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics.<n>HarmoWAM fully leverages a world model to unify predictive and reactive control, enabling both general transit and precise manipulation.<n>We construct three training-unseen test environments across six real-world robotic tasks, covering variations in background, position, and object semantics.
  arXiv  Detail & Related papers  (2026-05-11T17:59:56Z)
• AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites [18.635313325437664]
  We propose AGWM (Affordance-Grounded World Model), which learns an abstract affordance structure represented as a DAG of prerequisite dependencies to explicitly track the dynamic executability of actions.<n> Experiments on game-based simulated environments demonstrate the effectiveness of our method by achieving lower multi-step prediction error, better generalization to novel configurations, and improved interpretability.
  arXiv  Detail & Related papers  (2026-05-07T18:46:44Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• Ego-centric Predictive Model Conditioned on Hand Trajectories [52.531681772560724]
  In egocentric scenarios, anticipating both the next action and its visual outcome is essential for understanding human-object interactions.<n>We propose a unified two-stage predictive framework that jointly models action and visual future in egocentric scenarios.<n>Our approach is the first unified model designed to handle both egocentric human activity understanding and robotic manipulation tasks.
  arXiv  Detail & Related papers  (2025-08-27T13:09:55Z)
• From Marginal to Joint Predictions: Evaluating Scene-Consistent Trajectory Prediction Approaches for Automated Driving [4.795092023802721]
  Marginal prediction models commonly forecast each agent's future trajectories independently.<n>Joint prediction models explicitly account for the interactions between agents, yielding socially and physically consistent predictions.<n>We evaluate each approach in terms of prediction accuracy, multi-modality, and inference efficiency.
  arXiv  Detail & Related papers  (2025-07-07T17:58:53Z)
• Human locomotor control timescales depend on the environmental context and sensory input modality [37.48294298569551]
  We present a unified data-driven framework to quantify the control timescales.<n>We apply this framework across tasks including walking and running.<n>Our framework reveals the factors that influence locomotor foot placement control timescales.
  arXiv  Detail & Related papers  (2025-03-20T16:57:15Z)
• ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning [90.41852663775086]
  ACT-JEPA is a novel architecture that integrates imitation learning and self-supervised learning.<n>We train a policy to predict action sequences and abstract observation sequences.<n>Our experiments show that ACT-JEPA improves the quality of representations by learning temporal environment dynamics.
  arXiv  Detail & Related papers  (2025-01-24T16:41:41Z)
• Annealed Winner-Takes-All for Motion Forecasting [48.200282332176094]
  We show how an aWTA loss can be integrated with state-of-the-art motion forecasting models to enhance their performance.<n>Our approach can be easily incorporated into any trajectory prediction model normally trained using WTA.
  arXiv  Detail & Related papers  (2024-09-17T13:26:17Z)
• Bootstrapped model learning and error correction for planning with uncertainty in model-based RL [1.370633147306388]
  A natural aim is to learn a model that reflects accurately the dynamics of the environment. This paper explores the problem of model misspecification through uncertainty-aware reinforcement learning agents. We propose a bootstrapped multi-headed neural network that learns the distribution of future states and rewards.
  arXiv  Detail & Related papers  (2020-04-15T15:41:21Z)

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.