Related papers: A Survey of Imitation Learning Methods, Environments and Metrics

A Survey of Imitation Learning Methods, Environments and Metrics

URL: http://arxiv.org/abs/2404.19456v2
Date: Tue, 30 Jul 2024 08:58:51 GMT
Title: A Survey of Imitation Learning Methods, Environments and Metrics
Authors: Nathan Gavenski, Felipe Meneguzzi, Michael Luck, Odinaldo Rodrigues,
Abstract summary: Imitation learning is an approach in which an agent learns how to execute a task by trying to mimic how one or more teachers perform it. This learning approach offers a compromise between the time it takes to learn a new task and the effort needed to collect teacher samples for the agent. The field of imitation learning has received much attention from researchers in recent years, resulting in many new methods and applications.
Score: 9.967130899041651
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Imitation learning is an approach in which an agent learns how to execute a task by trying to mimic how one or more teachers perform it. This learning approach offers a compromise between the time it takes to learn a new task and the effort needed to collect teacher samples for the agent. It achieves this by balancing learning from the teacher, who has some information on how to perform the task, and deviating from their examples when necessary, such as states not present in the teacher samples. Consequently, the field of imitation learning has received much attention from researchers in recent years, resulting in many new methods and applications. However, with this increase in published work and past surveys focusing mainly on methodology, a lack of standardisation became more prominent in the field. This non-standardisation is evident in the use of environments, which appear in no more than two works, and evaluation processes, such as qualitative analysis, that have become rare in current literature. In this survey, we systematically review current imitation learning literature and present our findings by (i) classifying imitation learning techniques, environments and metrics by introducing novel taxonomies; (ii) reflecting on main problems from the literature; and (iii) presenting challenges and future directions for researchers.

Related papers

Scalable Language Model with Generalized Continual Learning [58.700439919096155]
The Joint Adaptive Re-ization (JARe) is integrated with Dynamic Task-related Knowledge Retrieval (DTKR) to enable adaptive adjustment of language models based on specific downstream tasks. Our method demonstrates state-of-the-art performance on diverse backbones and benchmarks, achieving effective continual learning in both full-set and few-shot scenarios with minimal forgetting.
arXiv Detail & Related papers (2024-04-11T04:22:15Z)
A Survey on Self-Supervised Representation Learning [2.5442795971328307]
A lot of methods were introduced that allow learning of image representations without supervision. The quality of these representations is close to supervised learning, while no labeled images are needed. This survey paper provides a comprehensive review of these methods in a unified notation, points out similarities and differences of these methods, and proposes a taxonomy which sets these methods in relation to each other.
arXiv Detail & Related papers (2023-08-22T14:05:37Z)
A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning [76.47138162283714]
Forgetting refers to the loss or deterioration of previously acquired information or knowledge. Forgetting is a prevalent phenomenon observed in various other research domains within deep learning. Survey argues that forgetting is a double-edged sword and can be beneficial and desirable in certain cases.
arXiv Detail & Related papers (2023-07-16T16:27:58Z)
Automatic Related Work Generation: A Meta Study [5.025654873456755]
In natural language processing, a literature review is usually conducted under the "Related Work" section. The task of automatic related work generation aims to automatically generate the "Related Work" section. We conduct a meta-study to compare the existing literature on related work generation from the perspectives of problem formulation, dataset collection, methodological approach, performance evaluation, and future prospects.
arXiv Detail & Related papers (2022-01-06T01:16:38Z)
Individual Explanations in Machine Learning Models: A Case Study on Poverty Estimation [63.18666008322476]
Machine learning methods are being increasingly applied in sensitive societal contexts. The present case study has two main objectives. First, to expose these challenges and how they affect the use of relevant and novel explanations methods. And second, to present a set of strategies that mitigate such challenges, as faced when implementing explanation methods in a relevant application domain.
arXiv Detail & Related papers (2021-04-09T01:54:58Z)
Learning Invariant Representation for Continual Learning [5.979373021392084]
A key challenge in Continual learning is catastrophically forgetting previously learned tasks when the agent faces a new one. We propose a new pseudo-rehearsal-based method, named learning Invariant Representation for Continual Learning (IRCL) Disentangling the shared invariant representation helps to learn continually a sequence of tasks, while being more robust to forgetting and having better knowledge transfer.
arXiv Detail & Related papers (2021-01-15T15:12:51Z)
Curriculum-Meta Learning for Order-Robust Continual Relation Extraction [12.494209368988253]
We propose a novel curriculum-meta learning method to tackle the challenges of continual relation extraction. We combine meta learning and curriculum learning to quickly adapt model parameters to a new task. We present novel difficulty-based metrics to quantitatively measure the extent of order-sensitivity of a given model.
arXiv Detail & Related papers (2021-01-06T08:52:34Z)
Knowledge as Invariance -- History and Perspectives of Knowledge-augmented Machine Learning [69.99522650448213]
Research in machine learning is at a turning point. Research interests are shifting away from increasing the performance of highly parameterized models to exceedingly specific tasks. This white paper provides an introduction and discussion of this emerging field in machine learning research.
arXiv Detail & Related papers (2020-12-21T15:07:19Z)
Towards Improved Model Design for Authorship Identification: A Survey on Writing Style Understanding [30.642840676899734]
Authorship identification tasks rely heavily on linguistic styles. Traditional machine learning methods based on handcrafted feature sets are already approaching their performance limits. We describe outstanding methods in style-related tasks in general and analyze how they are used in combination in the top-performing models.
arXiv Detail & Related papers (2020-09-30T05:17:42Z)
Importance Weighted Policy Learning and Adaptation [89.46467771037054]
We study a complementary approach which is conceptually simple, general, modular and built on top of recent improvements in off-policy learning. The framework is inspired by ideas from the probabilistic inference literature and combines robust off-policy learning with a behavior prior. Our approach achieves competitive adaptation performance on hold-out tasks compared to meta reinforcement learning baselines and can scale to complex sparse-reward scenarios.
arXiv Detail & Related papers (2020-09-10T14:16:58Z)
Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey [53.73359052511171]
Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback. We present a framework for curriculum learning (CL) in RL, and use it to survey and classify existing CL methods in terms of their assumptions, capabilities, and goals.
arXiv Detail & Related papers (2020-03-10T20:41:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.