paper-with-me

Papers

Inductive Generalization in Reinforcement Learning from Specifications

2024-06-05 · Vignesh Subramanian, Rohit Kushwah, Subhajit Roy, Suguman Bansal

We present a novel inductive generalization framework for RL from logical specifications. Many interesting tasks in RL environments have a natural inductive structure. These inductive tasks have similar overarching goals but they differ inductively in low-level predicates and distributions. We present a generalization procedure that leverages this inductive relationship to learn a higher-order function, a policy generator, that generates appropriately adapted policies for instances of an inductive task in a zero-shot manner. An evaluation of the proposed approach on a set of challenging control benchmarks demonstrates the promise of our framework in generalizing to unseen policies for long-horizon tasks.

📄 PDF Abstract BibTeX arXiv:2406.03651

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications

2026-05-30 · Vignesh Subramanian, Subhajit Roy, Suguman Bansal arxiv

Inductive generalization is a framework for reinforcement learning (RL) generalization in which inductively related task instances admit inductively related policies. Prior work captures this structure via a higher-order…

Zero-shot GeneralizationReinforcement Learning

Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning

2025-11-04 · Tiberiu-Andrei Georgescu, Alexander W. Goodall, Dalal Alrajeh, Francesco Belardinelli 외 arxiv

Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent's actions remain compliant with formal specifications. Classical shielding approaches, however, are often static, in the s…

Inductive logic programmingReinforcement Learning

In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications

2021-10-18 · ICLR 2022 4 · Borja G. León, Murray Shanahan, Francesco Belardinelli

We address the problem of building agents whose goal is to learn to execute out-of distribution (OOD) multi-task instructions expressed in temporal logic (TL) by using deep reinforcement learning (DRL). Recent works prov…

Deep Reinforcement Learning

Deep Reinforcement Learning via Object-Centric Attention

2025-04-03 · Jannis Blüml, Cedric Derstroff, Bjarne Gregori, Elisabeth Dillies 외

Deep reinforcement learning agents, trained on raw pixel inputs, often fail to generalize beyond their training environments, relying on spurious correlations and irrelevant background details. To address this issue, obj…

Deep Reinforcement LearningInductive BiasObjectreinforcement-learning+1

Inductive Biases for Zero-shot Systematic Generalization in Language-informed Reinforcement Learning

2025-01-25 · Negin Hashemi Dijujin, Seyed Roozbeh Razavi Rohani, Mohammad Mahdi Samiei, Mahdieh Soleymani Baghshah

Sample efficiency and systematic generalization are two long-standing challenges in reinforcement learning. Previous studies have shown that involving natural language along with other observation modalities can improve …

Decision MakingSystematic Generalization