paper-with-me

홈 › Papers

Behavior Cloned Transformers are Neurosymbolic Reasoners

2022-10-13 · Ruoyao Wang, Peter Jansen, Marc-Alexandre Côté, Prithviraj Ammanabrolu

In this work, we explore techniques for augmenting interactive agents with information from symbolic modules, much like humans use tools like calculators and GPS systems to assist with arithmetic and navigation. We test our agent's abilities in text games -- challenging benchmarks for evaluating the multi-step reasoning abilities of game agents in grounded, language-based environments. Our experimental study indicates that injecting the actions from these symbolic modules into the action space of a behavior cloned transformer agent increases performance on four text game benchmarks that test arithmetic, navigation, sorting, and common sense reasoning by an average of 22%, allowing an agent to reach the highest possible performance on unseen games. This action injection technique is easily extended to new agents, environments, and symbolic modules.

📄 PDF Abstract BibTeX arXiv:2210.07382

Code (1)

cognitiveailab/neurosymbolic 공식 구현 pytorch

Tasks

Common Sense Reasoning

Methods 이 논문이 사용한 방법론

Test 설명 없음
GPS Greedy Policy Search (GPS) is a simple algorithm that learns a policy for test-time data augmentation based on the predictive performance on a validation set. GPS starts with…

Similar Papers 제목 키워드 기반

Self-Supervised Behavior Cloned Transformers are Path Crawlers for Text Games

2023-12-07 · Ruoyao Wang, Peter Jansen

In this work, we introduce a self-supervised behavior cloning transformer for text games, which are challenging benchmarks for multi-step reasoning in virtual environments. Traditionally, Behavior Cloning Transformers ex…

Robustness of Neurosymbolic Reasoners on First-Order Logic Problems

2025-09-22 · Hannah Bansal, Kemal Kurniawan, Lea Frermann arxiv

Recent trends in NLP aim to improve reasoning capabilities in Large Language Models (LLMs), with key focus on generalization and robustness to variations in tasks. Counterfactual task variants introduce minimal but seman…

Large Language Models Are Neurosymbolic Reasoners

2024-01-17 · Meng Fang, Shilong Deng, Yudi Zhang, Zijing Shi 외

A wide range of real-world applications is characterized by their symbolic nature, necessitating a strong capability for symbolic reasoning. This paper investigates the potential application of Large Language Models (LLM…

Common Sense ReasoningMathtext-based gamesvalid

Neurosymbolic Reinforcement Learning and Planning: A Survey

2023-09-02 · K. Acharya, W. Raza, C. M. J. M. Dourado Jr, A. Velasquez 외

The area of Neurosymbolic Artificial Intelligence (Neurosymbolic AI) is rapidly developing and has become a popular research topic, encompassing sub-fields such as Neurosymbolic Deep Learning (Neurosymbolic DL) and Neuro…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Survey

Relational Neurosymbolic Markov Models

2024-12-17 · Lennert De Smet, Gabriele Venturato, Luc De Raedt, Giuseppe Marra

Sequential problems are ubiquitous in AI, such as in reinforcement learning or natural language processing. State-of-the-art deep sequential models, like transformers, excel in these settings but fail to guarantee the sa…

Bayesian Inference