A lifelong learning perspective for mobile robot control

By Sebastian Thrun. 1994

Subfields: Meta & Continual Learning, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Meta & Continual Learning

In Robotics & Control

Citations in the corpus

Lifelong Learning with Dynamically Expandable Networks (2017, positive): “Since its inception of idea by Thrun (1995), it has been extensively studied due to its practicality in scenarios where the data arrives in streams, such as in autonomous driving or learning of robotic agents.”
Gradient Episodic Memory for Continual Learning (2017, background): “Continual learning [Ring, 1994], also called lifelong learning [Thrun, 1994, Thrun and Pratt, 2012, Thrun, 1998, 1996], considers learning through a sequence of tasks, where the learner has to retain knowledge about past tasks and leverage that knowledge to quickly acquire new skills.”
The Challenges of Continuous Self-Supervised Learning (2022, background): “Continual and lifelong learning: The ability to continuously learn new concepts or tasks over time is often referred to as lifelong learning [75] or never-”
Architecture Matters in Continual Learning (2022, background): “Continual learning (CL) (Ring, 1995; Thrun, 1995) is a branch of machine learning where the model is exposed to a sequence of tasks with the hope of exploiting existing knowledge to adapt quickly to new tasks.”
Wide Neural Networks Forget Less Catastrophically (2021, background): “To overcome these inefﬁciencies, ﬁelds, such as continual learning (CL) (Ring, 1995) or lifelong learning (Thrun, 1995) are gaining a lot of attention recently.”
Representational Continuity for Unsupervised Continual Learning (2021, background): “Recently continual learning (Thrun, 1995) has gained a lot of attention in the deep learning community due to its ability to continually learn on a sequence of non-stationary tasks (Kumar & Daume III, 2012; Li & Hoiem, 2016) and close proximity to the human learning process (Flesch et al., 2018).”
Online Coreset Selection for Rehearsal-based Continual Learning (2021, neutral): “In light of this need, continual learning (CL) [40], or lifelong learning, tackles a learning scenario where a model continuously learns over a sequence of tasks [18, 25] within a broad research area, such as classification [15, 9], image generation [47], language learning [24, 4], clinical applicat”
Efficient Continual Learning with Modular Networks and Task-Driven Priors (2020, background): “Continual Learning (CL) is a learning framework whereby an agent learns through a sequence of tasks (Ring, 1994; Thrun, 1994; 1998), observing each task once and only once.”
A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix (2020, background): “Continual learning (CL) or lifelong learning [Thrun, 1995, Chen and Liu, 2018] has been one of the most important milestone on the path to building artiﬁcial general intelligence [Silver, 2011].”
Federated Continual Learning with Weighted Inter-client Transfer (2020, methodology): “Continual learning (1; 2; 3; 4; 5) describes a learning scenario where a model continuously trains on a sequence of tasks; it is inspired by the human learning process, as a person learns to perform numerous tasks with large diversity over his/her lifespan, making use of the past knowledge to learn ”
Compacting, Picking and Growing for Unforgetting Continual Learning (2019, background): “Continual lifelong learning [42, 28] has received much attention in recent deep learning studies.”
Scalable and Order-robust Continual Learning with Additive Parameter Decomposition (2019, background): “The literature on continual (lifelong) learning (Thrun, 1995) is vast (Ruvolo & Eaton, 2013) as it is a long-studied topic, but we only mention the most recent and relevant works.”
Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference (2018, background): “Such agents must incrementally learn and adapt to a changing environment while maintaining memories of what they have learned before, a setting known as lifelong learning (Thrun, 1994; 1996).”
Reinforced Continual Learning (2018, background): “Continual learning, or lifelong learning [13], the ability to learn consecutive tasks without forgetting how to perform previously trained tasks, is an important topic for developing artiﬁcial intelligence.”
Scalable Recollections for Continual Lifelong Learning (2017, background): “Continual learning (Thrun, 1994; Ring, 1994; Thrun, 1996; Thrun & Pratt, 1998; 2012) has three main requirements: (1) continually learn in a non-stationary environment, (2) retain memories which are useful, (3) manage time and memory resources over a long period of time.”
RoboNet: Large-Scale Multi-Robot Learning (2019, background): “The multi-task literature [18, 19], lifelong learning literature [20, 21], and meta-learning literature [22, 23] describe ideas that are tightly coupled with this concept.”
On the Soft-Subnetwork for Few-shot Class Incremental Learning (2022, background): “Lifelong Learning, or Continual Learning, is a learning paradigm to expand knowledge and skills through sequential training of multiple tasks [44].”
Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning (2023, background): “Continual learning [51], defined as the model’s ability to sequentially assimilate information from a continuous stream of potentially correlated data, is critical for modern intelligent systems, due to the inherently dynamic nature of the real world [19].”
Learning to Predict Gradients for Semi-Supervised Continual Learning (2022, methodology): “The tasks may vary over time, e.g . images with novel visual concepts ( i.e . classes) or addressing different problems from the previous tasks [3].”