LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.
hub
Efficient lifelong learning with A-GEM.CoRR, abs/1812.00420
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
abstract
In lifelong learning, the learner is presented with a sequence of tasks, incrementally building a data-driven prior which may be leveraged to speed up learning of a new task. In this work, we investigate the efficiency of current lifelong approaches, in terms of sample complexity, computational and memory cost. Towards this end, we first introduce a new and a more realistic evaluation protocol, whereby learners observe each example only once and hyper-parameter selection is done on a small and disjoint set of tasks, which is not used for the actual learning experience and evaluation. Second, we introduce a new metric measuring how quickly a learner acquires a new skill. Third, we propose an improved version of GEM (Lopez-Paz & Ranzato, 2017), dubbed Averaged GEM (A-GEM), which enjoys the same or even better performance as GEM, while being almost as computationally and memory efficient as EWC (Kirkpatrick et al., 2016) and other regularization-based methods. Finally, we show that all algorithms including A-GEM can learn even more quickly if they are provided with task descriptors specifying the classification tasks under consideration. Our experiments on several standard lifelong learning benchmarks demonstrate that A-GEM has the best trade-off between accuracy and efficiency.
hub tools
representative citing papers
SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
DRIFT is a benchmark for task-free continual graph learning under continuous distribution shifts, demonstrating that standard methods degrade without task boundary information.
MIST fixes unreliable splits in streaming decision trees for class-incremental learning by using a K-independent McDiarmid bound on Gini impurity, Bayesian moment projection for knowledge transfer, and KLL quantile sketches for adaptive leaf predictions.
TeLAPA maintains archives of behaviorally diverse yet competent policies aligned in a shared latent space to preserve plasticity and enable faster recovery after interference in continual reinforcement learning.
Sharpness-aware pretraining and related flat-minima interventions reduce catastrophic forgetting by up to 80% after post-training across 20M-150M models and by 31-40% at 1B scale.
Three complementary metrics are introduced to distinguish model adaptation from intrinsic data difficulty under temporal distribution shift.
Muon-OGD integrates Muon-style spectral-norm geometry with orthogonal gradient constraints to improve the stability-plasticity trade-off during sequential LLM adaptation.
HEDP uses energy regularization inspired by Helmholtz free energy plus hybrid energy-distance weighting in prompts to improve domain selection and achieve a 2.57% accuracy gain on benchmarks like CORe50 while mitigating catastrophic forgetting.
CRAFT is a continual learning method for LLMs that learns low-rank interventions on hidden representations, using a unified KL-divergence objective to handle task routing by output divergence, forgetting control via prior-state regularization, and intervention merging.
citing papers explorer
-
\emph{DRIFT}: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts
DRIFT is a benchmark for task-free continual graph learning under continuous distribution shifts, demonstrating that standard methods degrade without task boundary information.
-
MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
MIST fixes unreliable splits in streaming decision trees for class-incremental learning by using a K-independent McDiarmid bound on Gini impurity, Bayesian moment projection for knowledge transfer, and KLL quantile sketches for adaptive leaf predictions.
-
Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning
TeLAPA maintains archives of behaviorally diverse yet competent policies aligned in a shared latent space to preserve plasticity and enable faster recovery after interference in continual reinforcement learning.
-
Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
Sharpness-aware pretraining and related flat-minima interventions reduce catastrophic forgetting by up to 80% after post-training across 20M-150M models and by 31-40% at 1B scale.
-
Tracking Adaptation Time: Metrics for Temporal Distribution Shift
Three complementary metrics are introduced to distinguish model adaptation from intrinsic data difficulty under temporal distribution shift.
-
Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
Muon-OGD integrates Muon-style spectral-norm geometry with orthogonal gradient constraints to improve the stability-plasticity trade-off during sequential LLM adaptation.
-
CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning
CRAFT is a continual learning method for LLMs that learns low-rank interventions on hidden representations, using a unified KL-divergence objective to handle task routing by output divergence, forgetting control via prior-state regularization, and intervention merging.