Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling

• URL: http://arxiv.org/abs/2607.04409v1
• Date: Sun, 05 Jul 2026 17:02:40 GMT
• Title: Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling
• Abstract summary: We study how agents can learn world models with representations that are task-specific, minimal, and sufficient for decision-making.<n>We achieve this via a closed-loop synergy between the agent and the world model.
• Score: 44.18914219393549
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning and planning in imagination using world models provides an effective paradigm for training agents for decision-making. However, existing approaches often rely on high-dimensional latent spaces or generic visual embeddings that retain many factors irrelevant to control, limiting efficiency and generalization across tasks. To this end, we study how agents can learn world models with representations that are task-specific, minimal, and sufficient for decision-making. We achieve this via a closed-loop synergy between the agent and the world model, in which structured world-model learning distills task-sufficient representations from informative interaction data. On the agent side, agents actively probe the environment to collect informative trajectories that expose task-relevant latent factors, guided by an adaptive curriculum. On the world-model side, we learn structured representations over observations to distill compact, task-sufficient latent states from the collected interaction data. This synergy enables the empirical recovery of task-sufficient latent representations that capture all control-relevant factors. Leveraging these representations, the resulting policies achieve improved sample efficiency and generalization, including generalization across skills, object-skill compositions, and previously unseen tasks on standard continuous-control and robotic-manipulation benchmarks.

Related papers

• Contextual Latent World Models for Offline Meta Reinforcement Learning [17.917947576971816]
  We introduce contextual latent world models, which condition latent world models on inferred task representations and train them jointly with the context encoder.<n>This enforces task-conditioned temporal consistency, yielding task representations that capture task-dependent dynamics.<n>Our method learns more expressive task representations and significantly improves generalization to unseen tasks across MuJoCo, Contextual-DeepMind Control, and Meta-World benchmarks.
  arXiv  Detail & Related papers  (2026-03-03T12:45:20Z)
• Object-Centric World Models for Causality-Aware Reinforcement Learning [13.063093054280946]
  We propose emph Transformer Imagination with CAusality-aware reinforcement learning (ASTICA)<n>A unified framework in which object-centric Transformers serve as the world model and causality-aware policy and value networks.<n>Experiments on object-rich benchmarks demonstrate that STICA consistently outperforms state-of-the-art agents in both sample efficiency and final performance.
  arXiv  Detail & Related papers  (2025-11-18T08:53:09Z)
• Uniting contrastive and generative learning for event sequences models [51.547576949425604]
  This study investigates the integration of two self-supervised learning techniques - instance-wise contrastive learning and a generative approach based on restoring masked events in latent space.<n> Experiments conducted on several public datasets, focusing on sequence classification and next-event type prediction, show that the integrated method achieves superior performance compared to individual approaches.
  arXiv  Detail & Related papers  (2024-08-19T13:47:17Z)
• Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning [63.58935783293342]
  Causal Bisimulation Modeling (CBM) is a method that learns the causal relationships in the dynamics and reward functions for each task to derive a minimal, task-specific abstraction. CBM's learned implicit dynamics models identify the underlying causal relationships and state abstractions more accurately than explicit ones.
  arXiv  Detail & Related papers  (2024-01-23T05:43:15Z)
• Leveraging sparse and shared feature activations for disentangled representation learning [112.22699167017471]
  We propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. We validate our approach on six real world distribution shift benchmarks, and different data modalities.
  arXiv  Detail & Related papers  (2023-04-17T01:33:24Z)
• Investigating the role of model-based learning in exploration and transfer [11.652741003589027]
  In this paper, we investigate transfer learning in the context of model-based agents. We find that a model-based approach outperforms controlled model-free baselines for transfer learning. Our results show that intrinsic exploration combined with environment models present a viable direction towards agents that are self-supervised and able to generalize to novel reward functions.
  arXiv  Detail & Related papers  (2023-02-08T11:49:58Z)
• Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation [19.840186443344]
  We propose to use structured world models to incorporate inductive biases in the control loop to achieve sample-efficient exploration. Our method generates free-play behavior that starts to interact with objects early on and develops more complex behavior over time.
  arXiv  Detail & Related papers  (2022-06-22T22:08:50Z)
• Multi-Agent Imitation Learning with Copulas [102.27052968901894]
  Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions. In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems. Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents.
  arXiv  Detail & Related papers  (2021-07-10T03:49:41Z)
• Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
  One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy. We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
  arXiv  Detail & Related papers  (2020-07-14T16:42:59Z)

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.