[1907.00182] Continual Learning for Robotics

Continual learning (CL) is a particular machine learning paradigm where the data distribution and learning objective changes through time, or where all the training data and objective criteria are never available at once. The evolution of the learning process is modeled by a sequence of learning experiences where the goal is to be able to learn new skills all along the sequence without forgetting what has been previously learned. Continual learning also aims at the same time at optimizing the memory, the computation power and the speed during the learning process. An important challenge for machine learning is not necessarily finding solutions that work in the real world but rather finding stable algorithms that can learn in real world. Hence, the ideal approach would be tackling the real world in a embodied platform: an autonomous agent. Continual learning would then be effective in an autonomous agent or robot, which would learn autonomously through time about the external world, a

3 mentions: @NataliaDiazRodr@SoEngineering
Keywords: robotics
Date: 2019/07/03 03:48

Referring Tweets

@NataliaDiazRodr Still wondering what @ContinualAI or Lifelong learning is all about? not sure which papers to print for the beach this summer? We are here to help you with our survey on "Continual Learning for Robotics" :) w/ @TLesort @v_lomonaco @drFilliat t.co/Fu1qtzJFhv t.co/jmXp3l4L5j

Related Entries

Read more Frontiers | Bootstrapping Knowledge Graphs From Images and Text | Frontiers in Neurorobotics
0 users, 1 mentions 2019/12/07 00:51
Read more Data-Driven Robotics
0 users, 5 mentions 2019/09/27 15:48
Read more Knowledge Transfer Graph for Deep Collaborative Learning - The Robotics Institute Carnegie Mellon Un...
0 users, 2 mentions 2019/09/12 00:50
Read more GitHub - rlworkgroup/metaworld: An open source robotics benchmark for meta- and multi-task reinforce...
0 users, 1 mentions 2019/09/14 03:48