arXiv subjects

İlker Işık

Publications and source records attributed to İlker Işık.

7 recordsLinked to original sources

arXiv2026

Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning

Current neural architectures lack a principled way to handle interchangeable tokens, i.e., symbols that are semantically equivalent yet distinguishable, such as bound variables. As a result, models trained on fixed vocabularies often struggle to generalize to unseen symbols, even when the underlying semantics remain unchanged. We propose a novel Transformer-based mechanism that is provably invariant to the renaming of interchangeable tokens. Our approach employs parallel embedding streams to isolate the contribution of each interchangeable token in the input, combined with an aggregated attention mechanism that enables structured information sharing across streams. Experimental results confirm the theoretical guarantees of our method and demonstrate substantial performance gains on open-vocabulary tasks that require generalization to novel symbols. Project page: https://bu-depend-lab.github.io/Symbol-Invariant-Transformer/

cs.LG↗

arXiv2026

SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning

Specification-guided reinforcement learning (RL) provides a principled framework for encoding complex, temporally extended tasks using formal specifications such as linear temporal logic (LTL). While recent methods have shown promising results, their ability to generalize across unseen specifications and diverse environments remains insufficiently understood. In this work, we introduce SpecRLBench, a benchmark designed to evaluate the generalization capabilities of LTL-based specification-guided RL methods. The benchmark spans multiple difficulty levels across navigation and manipulation domains, incorporating both static and dynamic environments, diverse robot dynamics, and varied observation modalities. Through extensive empirical evaluation, we characterize the strengths and limitations of existing approaches and reveal the challenges that emerge as specification and environment complexity increase. SpecRLBench provides a structured platform for systematic comparison and supports the development of more generalizable specification-guided RL methods. Code is available at https://github.com/BU-DEPEND-Lab/SpecRLBench.

cs.LG↗

arXiv2025

One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning

Generalizing to complex and temporally extended task objectives and safety constraints remains a critical challenge in reinforcement learning (RL). Linear temporal logic (LTL) offers a unified formalism to specify such requirements, yet existing methods are limited in their abilities to handle nested long-horizon tasks and safety constraints, and cannot identify situations when a subgoal is not satisfiable and an alternative should be sought. In this paper, we introduce GenZ-LTL, a method that enables zero-shot generalization to arbitrary LTL specifications. GenZ-LTL leverages the structure of Büchi automata to decompose an LTL task specification into sequences of reach-avoid subgoals. Contrary to the current state-of-the-art method that conditions on subgoal sequences, we show that it is more effective to achieve zero-shot generalization by solving these reach-avoid problems \textit{one subgoal at a time} through proper safe RL formulations. In addition, we introduce a novel subgoal-induced observation reduction technique that can mitigate the exponential complexity of subgoal-state combinations under realistic assumptions. Empirical results show that GenZ-LTL substantially outperforms existing methods in zero-shot generalization to unseen LTL specifications.

cs.AI↗

arXiv2025

Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence

Language models lack the notion of interchangeable tokens: symbols that are semantically equivalent yet distinct, such as bound variables in formal logic. This limitation prevents generalization to larger vocabularies and hinders the model's ability to recognize alpha-equivalence, where renaming bound variables preserves meaning. We formalize this machine learning problem and introduce alpha-covariance, a metric for evaluating robustness to such transformations. To tackle this task, we propose a dual-part token embedding strategy: a shared component ensures semantic consistency, while a randomized component maintains token distinguishability. Compared to a baseline that relies on alpha-renaming for data augmentation, our approach demonstrates improved generalization to unseen tokens in linear temporal logic solving, propositional logic assignment prediction, and copying with an extendable vocabulary, while introducing a favorable inductive bias for alpha-equivalence. Our findings establish a foundation for designing language models that can learn interchangeable token representations, a crucial step toward more flexible and systematic reasoning in formal domains. Our code and project page are available at https://necrashter.github.io/interchangeable-token-embeddings

cs.CL↗

arXiv2024

Learning to Estimate System Specifications in Linear Temporal Logic using Transformers and Mamba

Temporal logic is a framework for representing and reasoning about propositions that evolve over time. It is commonly used for specifying requirements in various domains, including hardware and software systems, as well as robotics. Specification mining or formula generation involves extracting temporal logic formulae from system traces and has numerous applications, such as detecting bugs and improving interpretability. Although there has been a surge of deep learning-based methods for temporal logic satisfiability checking in recent years, the specification mining literature has been lagging behind in adopting deep learning methods despite their many advantages, such as scalability. In this paper, we introduce autoregressive models that can generate linear temporal logic formulae from traces, towards addressing the specification mining problem. We propose multiple architectures for this task: transformer encoder-decoder, decoder-only transformer, and Mamba, which is an emerging alternative to transformer models. Additionally, we devise a metric for quantifying the distinctiveness of the generated formulae and a straightforward algorithm to enforce the syntax constraints. Our experiments show that the proposed architectures yield promising results, generating correct and distinct formulae at a fraction of the compute cost needed for the combinatorial baseline.

cs.CL↗

arXiv2024

Optimal Policy Synthesis from A Sequence of Goal Sets with An Application to Electric Distribution System Restoration

Motivated by the post-disaster distribution system restoration problem, in this paper, we study the problem of synthesizing the optimal policy for a Markov Decision Process (MDP) from a sequence of goal sets. For each goal set, our aim is to both maximize the probability to reach and minimize the expected time to reach the goal set. The order of the goal sets represents their priority. In particular, our aim is to generate a policy that is optimal with respect to the first goal set, and it is optimal with respect to the second goal set among the policies that are optimal with respect to the first goal set and so on. To synthesize such a policy, we iteratively filter the applicable actions according to the goal sets. We illustrate the developed method over sample distribution systems and disaster scenarios.

eess.SY↗

arXiv2024

Field Teams Coordination for Earthquake-Damaged Distribution System Energization

The re-energization of electrical distribution systems in a post-disaster scenario is of grave importance as most modern infrastructure systems rely heavily on the presence of electricity. This paper introduces a method to coordinate the field teams for the optimal energization of an electrical distribution system after an earthquake-induced blackout. The proposed method utilizes a Markov Decision Process (MDP) to create an optimal energization strategy, which aims to minimize the expected time to energize each distribution system component. The travel duration of each team and the possible outcomes of the energization attempts are considered in the state transitions. The failure probabilities of the system components are computed using the fragility curves of structures and the Peak Ground Acceleration (PGA) values which are encoded to the MDP model via transition probabilities. Furthermore, the proposed solution offers several methods to determine the non-optimal actions during the construction of the MDP and eliminate them in order to improve the run-time performance without sacrificing the optimality of the solution.

eess.SY↗