When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited

• URL: http://arxiv.org/abs/2605.17017v1
• Date: Sat, 16 May 2026 14:33:34 GMT
• Title: When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited
• Abstract summary: We formulate BFM task-inference as a robust minimax optimization problem.<n>This is the first BFM-based framework that achieves robustness to dynamics shifts.<n>Results demonstrate that robust policy can be achieved entirely at task-inference time.
• Score: 9.403334073411722
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Behavior Foundation Models (BFMs) enable scalable imitation learning (IL) by pretraining task-agnostic representations that can be rapidly adapted to new tasks. However, existing BFMs assume fixed environment dynamics, limiting their robustness under real-world shifts such as changes in friction, actuation, or sensor noise. We address this by formulating BFM task-inference as a robust minimax optimization problem, enabling adaptation to worst-case dynamics perturbations without modifying pretraining. To the best of our knowledge, this is the first BFM-based framework that achieves robustness to dynamics shifts while relying solely on offline data from a single nominal environment. Our approach significantly outperforms standard BFM and robust offline IL baselines under dynamics shifts. These results demonstrate that robust policy can be achieved entirely at task-inference time, improving the practicality of BFMs in dynamic settings.

Related papers

• Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments [68.02342920827135]
  We propose NoisyAgent, an agentic training framework that explicitly incorporates environmental imperfections into the agent learning process.<n>We identify two major sources of interaction noise in real-world scenarios: user noise, which captures ambiguity and variability in user interaction, and tool noise, which reflects failures and anomalies in tool execution.<n>Extensive experiments demonstrate that our approach consistently improves agent robustness under noisy and dynamic environments.
  arXiv  Detail & Related papers  (2026-05-26T16:02:00Z)
• RFPrompt: Prompt-Based Expert Adaptation of the Large Wireless Model for Modulation Classification [7.858819231575403]
  We investigate prompt-based adaptation as a general mechanism for OOD transfer in wireless foundation models.<n>We propose RFPrompt, a parameter-efficient framework that introduces learnable deep prompt tokens while keeping the pretrained backbone frozen.<n>Results show that prompt-based adaptation consistently improves robustness under distribution shift and limited supervision.
  arXiv  Detail & Related papers  (2026-05-05T02:09:58Z)
• Adaptive Linear Path Model-Based Diffusion [52.84663832658799]
  We introduce Linear Path Model-Based Diffusion (LP-MBD), which replaces the variance-preserving schedule with a flow-matching linear probability path.<n>We also propose Adaptive LP-MBD (ALP-MBD), which leverages reinforcement learning to adjust diffusion steps and noise levels according to task complexity and environmental conditions.
  arXiv  Detail & Related papers  (2026-02-02T21:33:03Z)
• Aligning Agentic World Models via Knowledgeable Experience Learning [68.85843641222186]
  We introduce WorldMind, a framework that constructs a symbolic World Knowledge Repository by synthesizing environmental feedback.<n>WorldMind achieves superior performance compared to baselines with remarkable cross-model and cross-environment transferability.
  arXiv  Detail & Related papers  (2026-01-19T17:33:31Z)
• Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making [48.998030470623384]
  offline decision-making requires reliable behaviors from fixed datasets without further interaction.<n>We propose a compositional model-based diffusion framework consisting of: (i) a planner that generates diverse, task-aligned trajectories; (ii) a dynamics model that enforces consistency with the underlying system dynamics; and (iii) a ranker module that selects behaviors aligned with the task objectives.
  arXiv  Detail & Related papers  (2025-12-09T06:26:02Z)
• Balance Equation-based Distributionally Robust Offline Imitation Learning [8.607736795429638]
  Imitation Learning (IL) has proven highly effective for robotic and control tasks where manually designing reward functions or explicit controllers is infeasible.<n>Standard IL methods implicitly assume that the environment dynamics remain fixed between training and deployment.<n>We address this challenge through Balance Equation-based Distributionally Robust Offline Learning.<n>We formulate the problem as a distributionally robust optimization over an uncertainty set of transition models, seeking a policy that minimizes the imitation loss under the worst-case transition distribution.
  arXiv  Detail & Related papers  (2025-11-11T07:48:09Z)
• Flexible Locomotion Learning with Diffusion Model Predictive Control [46.432397190673505]
  We present Diffusion-MPC, which leverages a learned generative diffusion model as an approximate dynamics prior for planning.<n>Our design enables strong test-time adaptability, allowing the planner to adjust to new reward specifications without retraining.<n>We validate Diffusion-MPC on real world, demonstrating strong locomotion and flexible adaptation.
  arXiv  Detail & Related papers  (2025-10-05T14:51:13Z)
• Dynamic Manipulation of Deformable Objects in 3D: Simulation, Benchmark and Learning Strategy [88.8665000676562]
  Prior methods often simplify the problem to low-speed or 2D settings, limiting their applicability to real-world 3D tasks.<n>To mitigate data scarcity, we introduce a novel simulation framework and benchmark grounded in reduced-order dynamics.<n>We propose Dynamics Informed Diffusion Policy (DIDP), a framework that integrates imitation pretraining with physics-informed test-time adaptation.
  arXiv  Detail & Related papers  (2025-05-23T03:28:25Z)
• Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics [42.446740732573296]
  Behavioral Foundation Models (BFMs) proved successful in producing policies for arbitrary tasks in a zero-shot manner.<n>Here, we show that one of the methods from the BFM family, Forward-Backward (FB) representation, cannot distinguish between distinct dynamics.<n>We propose a FB model with a transformer-based belief estimator, which greatly facilitates zero-shot adaptation.
  arXiv  Detail & Related papers  (2025-05-19T14:12:19Z)
• Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment [55.91291559442884]
  This work develops a methodology that enables data-driven methods to continuously learn and optimize in a dynamic environment. We propose to build the notion of continual learning into the modeling process of learning wireless systems. Our design is based on a novel min-max formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2020-11-16T08:24:34Z)

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.