A Goal-Set Characterization of Task Composition in the Boolean Task Algebra

• URL: http://arxiv.org/abs/2606.04053v1
• Date: Tue, 02 Jun 2026 09:33:06 GMT
• Title: A Goal-Set Characterization of Task Composition in the Boolean Task Algebra
• Abstract summary: We formalize a collapse in the space of optimal extended Q-value functions.<n>In deterministic MDPs, every such function is fully determined by the universal and empty tasks.<n>We introduce a goal-set-based composition method that performs logical operations on goal sets.
• Score: 11.652221710150824
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Boolean Task Algebra (BTA) provides a principled framework for zero-shot task composition in reinforcement learning by equipping goal-reaching tasks with Boolean operations. We revisit its structural assumptions and formalize a collapse in the space of optimal extended Q-value functions: in deterministic MDPs, every such function is fully determined by the universal and empty tasks. This makes the logarithmic set of base tasks proposed in the original BTA formulation redundant. Building on this observation, we introduce a goal-set-based composition method that performs logical operations on goal sets and reconstructs composed value functions by selecting slices from the universal and empty value functions. This reduces learning costs for standard BTA and reduces composition time for both BTA and Skill Machines, while preserving policy performance. Experiments across tabular, visual, function-approximation, and continuous-control domains show that learning additional base tasks does not yield better performance. Finally, we study the stochastic setting and provide a counterexample showing that this collapse need not hold, that is, optimal composition may require accounting for exponentially many policies in the number of goals. Code is available at https://github.com/EduardoTerres/bta_paper.

Related papers

• Task-State Adaptation with Prototype Memory for Multi-Task Dense Prediction [65.90697836568579]
  We propose a multi-task dense prediction framework that estimates a compact task state from global visual context.<n>MemMTL refines it through a learnable task-state prototype memory.<n>A separate task-agnostic residual bank provides a common adaptation path.
  arXiv  Detail & Related papers  (2026-08-28T08:48:22Z)
• Diagnosing Compositional Generalization in Sequential Robot Tasks [47.24821158025177]
  This paper studies compositional generalization through the lens of instruction-space coverage.<n>We decompose the generalization gap into three sources: textitmarginal instruction shift, textitinstruction-compositional shift, and textitcontext-action shift
  arXiv  Detail & Related papers  (2026-07-31T17:59:59Z)
• 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)
• Variational Task Vector Composition [53.476598858325985]
  We propose variational task vector composition, where composition coefficients are taken as latent variables and estimated in a Bayesian inference framework.<n>Motivated by the observation of structural redundancy in task vectors, we introduce a Spike-and-Slab prior that promotes sparsity.<n>We develop a gated sampling mechanism that constructs a controllable posterior by filtering the composition coefficients based on both uncertainty and importance.
  arXiv  Detail & Related papers  (2025-09-21T02:46:02Z)
• Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic [24.40854328492979]
  We propose Task Vector Bases, a framework compressing $T$ task vectors into $M T$ basis vectors while preserving the functionality of task arithmetic.<n>By representing each task vector as a structured linear combination of basis atoms, our approach supports standard operations such as addition, negation, as well as more advanced arithmetic ones.
  arXiv  Detail & Related papers  (2025-02-03T03:18:26Z)
• Binning as a Pretext Task: Improving Self-Supervised Learning in Tabular Domains [0.565395466029518]
  We propose a novel pretext task based on the classical binning method. The idea is straightforward: reconstructing the bin indices (either orders or classes) rather than the original values. Our empirical investigations ascertain several advantages of binning.
  arXiv  Detail & Related papers  (2024-05-13T01:23:14Z)
• Task-Distributionally Robust Data-Free Meta-Learning [99.56612787882334]
  Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data. For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift ( TDS) and Task-Distribution Corruption (TDC)
  arXiv  Detail & Related papers  (2023-11-23T15:46:54Z)
• Value-Distributional Model-Based Reinforcement Learning [59.758009422067]
  Quantifying uncertainty about a policy's long-term performance is important to solve sequential decision-making tasks. We study the problem from a model-based Bayesian reinforcement learning perspective. We propose Epistemic Quantile-Regression (EQR), a model-based algorithm that learns a value distribution function.
  arXiv  Detail & Related papers  (2023-08-12T14:59:19Z)
• Learning Rational Subgoals from Demonstrations and Instructions [71.86713748450363]
  We present a framework for learning useful subgoals that support efficient long-term planning to achieve novel goals. At the core of our framework is a collection of rational subgoals (RSGs), which are essentially binary classifiers over the environmental states. Given a goal description, the learned subgoals and the derived dependencies facilitate off-the-shelf planning algorithms, such as A* and RRT.
  arXiv  Detail & Related papers  (2023-03-09T18:39:22Z)
• Goal Kernel Planning: Linearly-Solvable Non-Markovian Policies for Logical Tasks with Goal-Conditioned Options [54.40780660868349]
  We introduce a compositional framework called Linearly-Solvable Goal Kernel Dynamic Programming (LS-GKDP)<n>LS-GKDP combines the Linearly-Solvable Markov Decision Process (LMDP) formalism with the Options Framework of Reinforcement Learning.<n>We show how an LMDP with a goal kernel enables the efficient optimization of meta-policies in a lower-dimensional subspace defined by the task grounding.
  arXiv  Detail & Related papers  (2020-07-06T05:13:20Z)
• A Boolean Task Algebra for Reinforcement Learning [14.731788603429774]
  We formalise the logical composition of tasks as a Boolean algebra. We show that by learning goal-oriented value functions, an agent can solve new tasks with no further learning.
  arXiv  Detail & Related papers  (2020-01-06T04:46:25Z)

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.