Optimistic Task Inference for Behavior Foundation Models

• URL: http://arxiv.org/abs/2510.20264v1
• Date: Thu, 23 Oct 2025 06:36:18 GMT
• Title: Optimistic Task Inference for Behavior Foundation Models
• Abstract summary: OpTI-BFM is an optimistic decision criterion that guides BFMs in data collection for task inference.<n>We evaluate OpTI-BFM on established zero-shot benchmarks and observe that it enables successor-features-based BFMs to identify and optimize an unseen reward function.
• Score: 36.02038435371954
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Behavior Foundation Models (BFMs) are capable of retrieving high-performing policy for any reward function specified directly at test-time, commonly referred to as zero-shot reinforcement learning (RL). While this is a very efficient process in terms of compute, it can be less so in terms of data: as a standard assumption, BFMs require computing rewards over a non-negligible inference dataset, assuming either access to a functional form of rewards, or significant labeling efforts. To alleviate these limitations, we tackle the problem of task inference purely through interaction with the environment at test-time. We propose OpTI-BFM, an optimistic decision criterion that directly models uncertainty over reward functions and guides BFMs in data collection for task inference. Formally, we provide a regret bound for well-trained BFMs through a direct connection to upper-confidence algorithms for linear bandits. Empirically, we evaluate OpTI-BFM on established zero-shot benchmarks, and observe that it enables successor-features-based BFMs to identify and optimize an unseen reward function in a handful of episodes with minimal compute overhead. Code is available at https://github.com/ThomasRupf/opti-bfm.

Related papers

• Exploration and Online Transfer with Behavioral Foundation Models [3.015354201629835]
  We show that it is possible to frame this online learning problem in terms of a bandit-like exploration-exploitation problem.<n>We derive a formulation inspired by Upper Confidence Bound and show that exploration can be achieved through the minimization of the eigenvalues of an uncertainty matrix.
  arXiv  Detail & Related papers  (2026-06-29T08:55:24Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning [82.925106913459]
  Reinforcement finetuning (RFT) is a key technique for aligning Large Language Models (LLMs) with human preferences and enhancing reasoning.<n>We introduce BOTS, a unified framework for Bayesian Online Task Selection in RFT reinforcement finetuning.
  arXiv  Detail & Related papers  (2025-10-30T11:15:23Z)
• Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment [16.352863226512984]
  Test-time adaptation (TTA) enhances the zero-shot robustness under distribution shifts by leveraging unlabeled test data during inference.<n>Most methods rely on backpropagation or iterative optimization, which limits scalability and hinders real-time deployment.<n>We propose ADAPT, an Advanced Distribution-Aware and back propagation-free Test-time adaptation method.
  arXiv  Detail & Related papers  (2025-08-21T13:42:49Z)
• Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits [58.63897489864948]
  Reinforcement learning with outcome-based feedback faces a fundamental challenge.<n>How do we assign credit to the right actions?<n>This paper provides the first comprehensive analysis of this problem in online RL with general function approximation.
  arXiv  Detail & Related papers  (2025-05-26T17:44:08Z)
• Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference [15.038210624870656]
  Reward inference is a critical intermediate step in the Reinforcement Learning from Human Feedback pipeline.<n>This paper develops two RLHF algorithms without reward inference for general RL problems beyond bandits and deterministic MDP bandit, and general preference models beyond the Bradley-Terry model.
  arXiv  Detail & Related papers  (2024-09-25T22:20:11Z)
• Self-Contrastive Forward-Forward Algorithm [3.1361717406527667]
  Forward-Forward (FF) algorithm relies on feedforward operations to optimize layer-wise objectives.<n>FF has failed to reach state-of-the-art performance on most standard benchmark tasks.<n>We propose Self-Contrastive Forward-Forward (SCFF) algorithm, a competitive training method aimed at closing this performance gap.
  arXiv  Detail & Related papers  (2024-09-17T22:58:20Z)
• Exploring validation metrics for offline model-based optimisation with diffusion models [50.404829846182764]
  In model-based optimisation (MBO) we are interested in using machine learning to design candidates that maximise some measure of reward with respect to a black box function called the (ground truth) oracle. While an approximation to the ground oracle can be trained and used in place of it during model validation to measure the mean reward over generated candidates, the evaluation is approximate and vulnerable to adversarial examples. This is encapsulated under our proposed evaluation framework which is also designed to measure extrapolation.
  arXiv  Detail & Related papers  (2022-11-19T16:57:37Z)
• Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes [70.80716221080118]
  The paper takes a generative perspective on policy evaluation via temporal-difference (TD) learning. The OS-GPTD approach is developed to estimate the value function for a given policy by observing a sequence of state-reward pairs. To alleviate the limited expressiveness associated with a single fixed kernel, a weighted ensemble (E) of GP priors is employed to yield an alternative scheme.
  arXiv  Detail & Related papers  (2021-12-01T23:15:09Z)
• Mutual-Information Based Few-Shot Classification [34.95314059362982]
  We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task. We propose a new alternating-direction solver, which speeds up transductive inference over gradient-based optimization.
  arXiv  Detail & Related papers  (2021-06-23T09:17:23Z)
• Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration [143.43658264904863]
  We show how iteration under a more standard notion of low inherent Bellman error, typically employed in least-square value-style algorithms, can provide strong PAC guarantees on learning a near optimal value function. We present a computationally tractable algorithm for the reward-free setting and show how it can be used to learn a near optimal policy for any (linear) reward function.
  arXiv  Detail & Related papers  (2020-08-18T04:34:21Z)
• Finding Optimal Points for Expensive Functions Using Adaptive RBF-Based Surrogate Model Via Uncertainty Quantification [11.486221800371919]
  We propose a novel global optimization framework using adaptive Radial Basis Functions (RBF) based surrogate model via uncertainty quantification. It first employs an RBF-based Bayesian surrogate model to approximate the true function, where the parameters of the RBFs can be adaptively estimated and updated each time a new point is explored. It then utilizes a model-guided selection criterion to identify a new point from a candidate set for function evaluation.
  arXiv  Detail & Related papers  (2020-01-19T16:15:55Z)

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.