A comprehensive survey of continual learning: theory, method and application
To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …
Continual learning: Applications and the road forward
Continual learning is a sub-field of machine learning, which aims to allow machine learning
models to continuously learn on new data, by accumulating knowledge without forgetting …
models to continuously learn on new data, by accumulating knowledge without forgetting …
COOM: a game benchmark for continual reinforcement learning
The advancement of continual reinforcement learning (RL) has been facing various
obstacles, including standardized metrics and evaluation protocols, demanding …
obstacles, including standardized metrics and evaluation protocols, demanding …
Towards anytime fine-tuning: Continually pre-trained language models with hypernetwork prompt
Continual pre-training has been urgent for adapting a pre-trained model to a multitude of
domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is …
domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is …
Learning to Modulate pre-trained Models in RL
Reinforcement Learning (RL) has been successful in various domains like robotics, game
playing, and simulation. While RL agents have shown impressive capabilities in their …
playing, and simulation. While RL agents have shown impressive capabilities in their …
Continual task allocation in meta-policy network via sparse prompting
How to train a generalizable meta-policy by continually learning a sequence of tasks? It is a
natural human skill yet challenging to achieve by current reinforcement learning: the agent is …
natural human skill yet challenging to achieve by current reinforcement learning: the agent is …
CaDeT: a Causal Disentanglement Approach for Robust Trajectory Prediction in Autonomous Driving
M Pourkeshavarz, J Zhang… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
For safe motion planning in real-world autonomous vehicles require behavior prediction
models that are reliable and robust to distribution shifts. The recent studies suggest that the …
models that are reliable and robust to distribution shifts. The recent studies suggest that the …
OER: Offline Experience Replay for Continual Offline Reinforcement Learning
S Gai, D Wang, L He - arXiv preprint arXiv:2305.13804, 2023 - arxiv.org
The capability of continuously learning new skills via a sequence of pre-collected offline
datasets is desired for an agent. However, consecutively learning a sequence of offline tasks …
datasets is desired for an agent. However, consecutively learning a sequence of offline tasks …
Libero: Benchmarking knowledge transfer for lifelong robot learning
Lifelong learning offers a promising paradigm of building a generalist agent that learns and
adapts over its lifespan. Unlike traditional lifelong learning problems in image and text …
adapts over its lifespan. Unlike traditional lifelong learning problems in image and text …
DGTRL: Deep graph transfer reinforcement learning method based on fusion of knowledge and data
G Chen, J Qi, Y Gao, X Zhu, Z Dong, Y Sun - Information Sciences, 2024 - Elsevier
Deep reinforcement learning has shown promising application effects in many fields.
However, issues such as low sample efficiency and weak knowledge transfer and …
However, issues such as low sample efficiency and weak knowledge transfer and …