Add to ORKGActive learning (AL) prioritizes the labeling of the most informative data samples. However, the performance of AL heuristics depends on the structure of the underlying classifier model and the data. We propose an imitation learning scheme that imitates the selection of the best expert heuristic at each stage of the AL cycle in a batch-mode pool-based setting. We use DAGGER to train the policy on a dataset and later apply it to datasets from similar domains. With multiple AL heuristics as experts, the policy is able to reflect the choices of the best AL heuristics given the current state of the AL process. Our experiment on well-known datasets show that we both outperform state of the art imitation learners and heuristics.Comment: 17 page
Active Learning (AL) for semantic segmentation is challenging due to heavy class imbalance and diffe...
Pool-based active learning is an important technique that helps reduce labeling efforts within a poo...
Active learning (AL) is a machine learning algorithm that can achieve greater accuracy with fewer la...
Active learning (AL) is a prominent technique for reducing the annotation effort required for traini...
Active Learning (AL) is a well-known standard method for efficiently obtaining annotated data by fir...
Heuristic-based active learning (AL) methods are limited when the data distribution of the underlyin...
Active Learning (AL) is a family of machine learning (ML) algorithms that predates the current era o...
Pool-based active learning (AL) is a promising technology for increasing data-efficiency of machine ...
Reinforcement learning (RL) provides a powerful framework for decision-making, but its application i...
Object classification by learning from data is a vast area of statistics and machine learning. Withi...
Many existing imitation learning datasets are collected from multiple demonstrators, each with diffe...
Offline imitation from observations aims to solve MDPs where only task-specific expert states and ta...
Traditional supervised machine learning algorithms are expected to have access to a large corpus of ...
In this work we discuss the problem of active learning. We present an approach that is based on A-op...
Adversarial imitation learning (AIL) has become a popular alternative to supervised imitation learni...
Active Learning (AL) for semantic segmentation is challenging due to heavy class imbalance and diffe...
Pool-based active learning is an important technique that helps reduce labeling efforts within a poo...
Active learning (AL) is a machine learning algorithm that can achieve greater accuracy with fewer la...
Active learning (AL) is a prominent technique for reducing the annotation effort required for traini...
Active Learning (AL) is a well-known standard method for efficiently obtaining annotated data by fir...
Heuristic-based active learning (AL) methods are limited when the data distribution of the underlyin...
Active Learning (AL) is a family of machine learning (ML) algorithms that predates the current era o...
Pool-based active learning (AL) is a promising technology for increasing data-efficiency of machine ...
Reinforcement learning (RL) provides a powerful framework for decision-making, but its application i...
Object classification by learning from data is a vast area of statistics and machine learning. Withi...
Many existing imitation learning datasets are collected from multiple demonstrators, each with diffe...
Offline imitation from observations aims to solve MDPs where only task-specific expert states and ta...
Traditional supervised machine learning algorithms are expected to have access to a large corpus of ...
In this work we discuss the problem of active learning. We present an approach that is based on A-op...
Adversarial imitation learning (AIL) has become a popular alternative to supervised imitation learni...
Active Learning (AL) for semantic segmentation is challenging due to heavy class imbalance and diffe...
Pool-based active learning is an important technique that helps reduce labeling efforts within a poo...
Active learning (AL) is a machine learning algorithm that can achieve greater accuracy with fewer la...