Learning from Failure [Extended Abstract]

被引：0
|
作者：
Grollman, Daniel H. [1 ]
Billard, Aude G. [1 ]
机构：
[1] Ecole Polytech Fed Lausanne, Learning Algorithms & Syst Lab, Lausanne, Switzerland
来源：
PROCEEDINGS OF THE 6TH ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTIONS (HRI 2011) | 2011年
关键词：
Learning from Demonstration;
D O I：
10.1145/1957656.1957703
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
In the canonical Robot Learning from Demonstration scenario a robot observes performances of a task and then develops an autonomous controller. Current work acknowledges that humans may be suboptimal demonstrators and refines the controller for improved performance. However, there is still an assumption that the demonstrations are successful examples of the task. We here consider the possibility that the human has failed, and propose a model to minimize the possibility of the robot making the same mistakes.
引用
收藏
页码：145 / 146
页数：2
相关论文
共 50 条
  • [1] Introspective Reinforcement Learning and Learning from Demonstration Extended Abstract
    Li, Mao
    Brys, Tim
    Kudenko, Daniel
    [J]. PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS (AAMAS' 18), 2018, : 1992 - 1994
  • [2] Learning Explanatory Rules from Noisy Data (Extended Abstract)
    Evans, Richard
    Grefenstette, Edward
    [J]. PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2018, : 5598 - 5602
  • [3] Failure diagnosis of declarative programs based on abstract interpretation (extended abstract)
    Musumbu, K
    [J]. COMPUTERS AND THEIR APPLICATIONS, 2000, : 431 - 434
  • [4] From Feature to Paradigm: Deep Learning in Machine Translation (Extended Abstract)
    Costa-jussa, Marta R.
    [J]. PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2018, : 5583 - 5587
  • [5] Learning Probabilistic logic models from probabilistic examples (Extended abstract)
    Chen, Jianzhong
    Muggleton, Stephen
    Santos, Jose
    [J]. INDUCTIVE LOGIC PROGRAMMING, 2008, 4894 : 22 - +
  • [6] Deep Residual Reinforcement Learning (Extended Abstract)
    Zhang, Shangtong
    Boehmer, Wendelin
    Whiteson, Shimon
    [J]. PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 4869 - 4873
  • [7] Learning Causal Effects on Hypergraphs (Extended Abstract)
    Ma, Jing
    Wan, Mengting
    Yang, Longqi
    Li, Jundong
    Hecht, Brent
    Teevan, Jaime
    [J]. PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 6463 - 6467
  • [8] Statistical Learning with a Nuisance Component (Extended Abstract)
    Foster, Dylan J.
    Syrgkanis, Vasilis
    [J]. CONFERENCE ON LEARNING THEORY, VOL 99, 2019, 99
  • [9] Some elements of machine learning (Extended abstract)
    Quinlan, JR
    [J]. MACHINE LEARNING, PROCEEDINGS, 1999, : 523 - 525
  • [10] Some elements of machine learning - (Extended abstract)
    Quinlan, JR
    [J]. INDUCTIVE LOGIC PROGRAMMING, 1999, 1634 : 15 - 18
12345