Papers Learning to Execute
“Learning to Execute” 태그가 달린 논문 25편 · 필터 해제
Few is More: Task-Efficient Skill-Discovery for Multi-Task Offline Multi-Agent Reinforcement Learning
As a data-driven approach, offline MARL learns superior policies solely from offline datasets, ideal for domains rich in historical data but with high interaction costs and risks. However, most existing methods are task-…
Learning to ExecuteMulti-agent Reinforcement LearningQ-Learningλ: A Benchmark for Data-Efficiency in Long-Horizon Indoor Mobile Manipulation Robotics
Learning to execute long-horizon mobile manipulation tasks is crucial for advancing robotics in household and workplace settings. However, current approaches are typically data-inefficient, underscoring the need for impr…
BenchmarkingDiversityLearning to ExecuteMotion Planning+1Learning Linear Attention in Polynomial Time
Previous research has explored the computational expressivity of Transformer models in simulating Boolean circuits or Turing machines. However, the learnability of these simulators from observational data has remained an…
Learning to ExecutePAC learningNAR-*ICP: Neural Execution of Classical ICP-based Pointcloud Registration Algorithms
This study explores the intersection of neural networks and classical robotics algorithms through the Neural Algorithmic Reasoning (NAR) framework, allowing to train neural networks to effectively reason like classical r…
Graph Neural NetworkLearning to ExecuteConditional Information Gain Trellis
Conditional computing processes an input using only part of the neural network's computational units. Learning to execute parts of a deep convolutional network by routing individual samples has several advantages: Reduci…
Learning to ExecuteMimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation
Tactile sensing is critical to fine-grained, contact-rich manipulation tasks, such as insertion and assembly. Prior research has shown the possibility of learning tactile-guided policy from teleoperated demonstration dat…
Contact-rich ManipulationImitation LearningLearning to Executereinforcement-learningEchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning
Language models are achieving impressive performance on various tasks by aggressively adopting inference-time prompting techniques, such as zero-shot and few-shot prompting. In this work, we introduce EchoPrompt, a simpl…
Date UnderstandingGSM8KIn-Context LearningLearning to Execute+3Latent Space Representations of Neural Algorithmic Reasoners
Neural Algorithmic Reasoning (NAR) is a research area focused on designing neural architectures that can reliably capture classical computation, usually by learning to execute algorithms. A typical approach is to rely on…
Graph Neural NetworkLearning to ExecuteTripletA Generalist Neural Algorithmic Learner
The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution. While recent years have seen a surge in methodological improvements in …
Graph Neural NetworkLearning to ExecuteUnveiling Transformers with LEGO: a synthetic reasoning task
We propose a synthetic reasoning task, LEGO (Learning Equality and Group Operations), that encapsulates the problem of following a chain of reasoning, and we study how the Transformer architectures learn this task. We pa…
Learning to ExecuteThe CLRS Algorithmic Reasoning Benchmark
Learning representations of algorithms is an emerging area of machine learning, seeking to bridge concepts from neural networks with classical algorithms. Several important works have investigated whether neural networks…
Learning to ExecuteLeveraging Relaxed Equilibrium by Lazy Transition for Sequence Modeling
In sequence modeling, certain tokens are usually less ambiguous than others, and representations of these tokens require fewer refinements for disambiguation. However, given the nature of attention-based models like Tran…
LAMBADALearning to ExecuteMachine TranslationTranslationLearning to Execute Actions or Ask Clarification Questions
Collaborative tasks are ubiquitous activities where a form of communication is required in order to reach a joint goal. Collaborative building is one of such tasks. We wish to develop an intelligent builder agent in a si…
Learning to ExecuteMinecraftGraph Neural Networks are Dynamic Programmers
Recent advances in neural algorithmic reasoning with graph neural networks (GNNs) are propped up by the notion of algorithmic alignment. Broadly, a neural network will be better at learning to execute a reasoning task (i…
Abstract AlgebraLearning to ExecuteStatic Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions
The execution behavior of a program often depends on external resources, such as program inputs or file contents, and so cannot be run in isolation. Nevertheless, software developers benefit from fast iteration loops whe…
BIG-bench Machine LearningInductive BiasLearning to ExecuteLearning to execute or ask clarification questions
Collaborative tasks are ubiquitous activities where a form of communication is required in order to reach a joint goal. Collaborative building is one of such tasks. To this end, we wish to develop an intelligent builder …
Learning to ExecuteMinecraftLearning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics
Applications of Reinforcement Learning (RL) in robotics are often limited by high data demand. On the other hand, approximate models are readily available in many robotics scenarios, making model-based approaches like pl…
Learning to ExecuteReinforcement Learning (RL)How to transfer algorithmic reasoning knowledge to learn new algorithms?
Learning to execute algorithms is a fundamental problem that has been widely studied. Prior work~\cite{veli19neural} has shown that to enable systematic generalisation on graph algorithms it is critical to have access to…
Learning to ExecuteMulti-Task LearningProTo: Program-Guided Transformer for Program-Guided Tasks
Programs, consisting of semantic and structural information, play an important role in the communication between humans and agents. Towards learning general program executors to unify perception, reasoning, and decision …
Decision MakingLearning to ExecuteMinecraftVisual Question Answering (VQA)+1Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
Graph neural networks (GNNs) have emerged as a powerful tool for learning software engineering tasks including code completion, bug finding, and program repair. They benefit from leveraging program structure like control…
Code CompletionLearning to ExecuteProgram RepairProgram Synthesis+1