Lifelong robot learning

By Sebastian Thrun, Tom Michael Mitchell. 1993

How researchers see this paper

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

In Reinforcement Learning

Citations in the corpus

Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019, background): “…learning (Lake et al., 2011; Romera-Paredes and Torr, 2015; Vinyals et al., 2016; Pan and Yang, 2010), meta-learning and life-long learning (Thrun and Mitchell, 1995; Silver et al., 2013; Chen and Liu, 2016; Parisi et al., 2018; Golkar et al., 2019; Sodhani et al., 2018; Lopez-Paz et al.,…”
The Arcade Learning Environment: An Evaluation Platform for General Agents (2012, background): “Similar ideas have been developed around the theme of lifelong learning : learning a reusable, highlevel understanding of the world from raw sensory data (Thrun & Mitchell, 1995; Pierce & Kuipers, 1997; Stober & Kuipers, 2008; Sutton et al., 2011).”
Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents (2017, background): “One traditional goal in reinforcement learning is for agents to continually improve their performance as they obtain more data (Hutter, 2005; Ring, 1997; Singh, Barto, & Chentanez, 2004; Sutton et al., 2011; Thrun & Mitchell, 1993; Wilson, 1985).”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, neutral): “Remedies to this problem can include using the original model outputs as supervision signals [7, 36, 52], or, as advocated in [28], considering the sensitivity of other tasks when updating shared parameters.”
Continual Lifelong Learning with Neural Networks: A Review (2018, background): “This is due to the tendency of learning models to catastrophically forget existing knowledge when learning from novel observations (Thrun and Mitchell, 1995).”
On the role of neurogenesis in overcoming catastrophic forgetting (2018, background): “llows: a(t) = exp( d b); (4) thus yielding the highest activation value of 1 when the network can perfectly match the input sequence (d b = 0). Each neuron is equipped with a habituation counter h j 2[0;1] expressing how frequently it has ﬁred based on a simpliﬁed model of how the efﬁcacy of a habit”
Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization (2018, background): “Effective models of lifelong learning are crucial in real-world conditions where an autonomous agent cannot be provided with all the necessary prior knowledge to interact with the environment and the direct access to previous experience is restricted (Thrun and Mitchell, 1995).”
Overcoming catastrophic forgetting with hard attention to the task (2018, background): “Apart from being more biologically plausible (Clegg et al., 1998), there are many practical situations which require a sequential learning system (cf. Thrun & Mitchell, 1995).”
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “This type of learning, advocated in AI and robotics systems (Thrun and Mitchell, 1995), is currently still missing in EPANNs.”
A Deep Hierarchical Approach to Lifelong Learning in Minecraft (2016, background): “This is one of the fundamental learning problems in AI [Thrun and Mitchell, 1995; Eaton and Ruvolo, 2013].”
The Ideal Continual Learner: An Agent That Never Forgets (2023, background): “The goal of building intelligent machines that are adaptive and self-improving over time has given rise to the continual learning paradigm, where the learner needs to solve multiple tasks presented sequentially (Thrun & Mitchell, 1995).”
Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions (2022, background): “Continual learning in practice The study of continual learning (or lifelong learning) dates back to the work of [34] and it receives a surge of research interest over recent years [14, 17, 10, 5, 13, 29, 32, 16, 27, 37].”
ConTinTin: Continual Learning from Task Instructions (2022, background): “cumulate knowledge from tasks learned in the past (S1) (Richard, 1970; Thrun and Mitchell, 1995; Chomsky, 2002); the other is to learn from natural instructions (S2) describing a high-level story about target tasks (Goldwasser and Roth, 2014).”
An Empirical Investigation of the Role of Pre-training in Lifelong Learning (2021, background): “In contrast, the lifelong learning (Thrun and Mitchell, 1995; Thrun, 1996; Chen and Liu, 2018) or incremental learning (Solomonoff et al.”
GCR: Gradient Coreset based Replay Buffer Selection for Continual Learning (2021, neutral): “The field of continual learning (CL) [44] studies the training of models in an incremental fashion, to generalize across a number of sequentially encountered scenarios or tasks, and to avoid the training & maintenance costs of one-off models.”
LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5 (2021, background): “Researchers in Lifelong Learning (Thrun & Mitchell, 1995) have proposed a number of methods to alleviate the above issues with machine learning.”
DER: Dynamically Expandable Representation for Class Incremental Learning (2021, background): “Such capability is indispensable for many real-world applications such as the intelligent robot [31], face recognition [19] and autonomous driving [25].”
Gradient Projection Memory for Continual Learning (2021, background): “In stark contrast, Artiﬁ-cial Neural Networks (ANNs) under such Continual Learning (CL) paradigm (Ring, 1998; Thrun & Mitchell, 1995; Lange et al., 2021) forget the information learned in the past tasks upon learning new ones.”
IIRC: Incremental Implicitly-Refined Classification (2020, background): “Lifelong Learning is a broad, multi-disciplinary, and expansive research domain with several synonyms: Incremental Learning [42], Continual Learning [48], and Never End-ing Learning [35].”
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting (2020, background): “The ﬁeld of continual learning or lifelong learning (Thrun & Mitchell, 1995; Silver et al., 2013) aims at maintaining previous performance and avoiding so-called catastrophic forgetting of previous experience (McCloskey & Cohen, 1989; McClelland et al., 1995) when learning new skills.”