Author image not provided
 Michael L Littman

Authors:
Add personal information
  Affiliation history
Bibliometrics: publication history
Average citations per article6.81
Citation Count109
Publication count16
Publication years2010-2017
Available for download8
Average downloads per article314.63
Downloads (cumulative)2,517
Downloads (12 Months)634
Downloads (6 Weeks)87
SEARCH
ROLE
Arrow RightAuthor only


AUTHOR'S COLLEAGUES
See all colleagues of this author

SUBJECT AREAS
See all subject areas




BOOKMARK & SHARE


16 results found Export Results: bibtexendnoteacmrefcsv

Result 1 – 16 of 16
Sort by:

1
May 2017 AAMAS '17: Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems
Publisher: International Foundation for Autonomous Agents and Multiagent Systems
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 5,   Downloads (12 Months): 39,   Downloads (Overall): 56

Full text available: PDFPDF
Existing machine-learning work has shown that algorithms can benefit from curricula---learning first on simple examples before moving to more difficult examples. While most existing work on curriculum learning focuses on developing automatic methods to iteratively select training examples with increasing difficulty tailored to the current ability of the learner, relatively ...
Keywords: curriculum learning, curriculum design, sequential decision tasks, human-agent interaction

2
December 2016 NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing Systems
Publisher: Curran Associates Inc.
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 0,   Downloads (12 Months): 0,   Downloads (Overall): 0

Full text available: PDFPDF
People often learn from others' demonstrations, and inverse reinforcement learning (IRL) techniques have realized this capacity in machines. In contrast, teaching by demonstration has been less well studied computationally. Here, we develop a Bayesian model for teaching by demonstration. Stark differences arise when demonstrators are intentionally teaching (i.e. showing) a ...

3
May 2016 AAMAS '16: Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems
Publisher: International Foundation for Autonomous Agents and Multiagent Systems
Bibliometrics:
Citation Count: 4
Downloads (6 Weeks): 6,   Downloads (12 Months): 41,   Downloads (Overall): 95

Full text available: PDFPDF
As robots become pervasive in human environments, it is important to enable users to effectively convey new skills without programming. Most existing work on Interactive Reinforcement Learning focuses on interpreting and incorporating non-expert human feedback to speed up learning; we aim to design a better representation of the learning agent ...
Keywords: eliciting human feedback, variable speed agents, crowdsourcing experiments, human-agent interaction, learning sequential decision tasks from humans

4 published by ACM
May 2016 CHI '16: Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems
Publisher: ACM
Bibliometrics:
Citation Count: 21
Downloads (6 Weeks): 38,   Downloads (12 Months): 226,   Downloads (Overall): 525

Full text available: PDFPDF
While researchers have long investigated end-user programming using a trigger-action (if-then) model, the website IFTTT is among the first instances of this paradigm being used on a large scale. To understand what IFTTT users are creating, we scraped the 224,590 programs shared publicly on IFTTT as of September 2015 and ...
Keywords: end-user composition, end-user programming, ifttt, internet of things (iot), trigger-action programming

5 published by ACM
April 2016 [email protected] '16: Proceedings of the Third (2016) ACM Conference on Learning @ Scale
Publisher: ACM
Bibliometrics:
Citation Count: 1
Downloads (6 Weeks): 5,   Downloads (12 Months): 21,   Downloads (Overall): 107

Full text available: PDFPDF
We propose a comparative judgement scheme for grading short answer questions in an online class. The scheme works by asking students to answer short answer questions. Then a multiple choice question is created whose choices are the answers given by students. We show that we can formulate a probabilistic graphical ...
Keywords: crowd sourcing, peer grading

6 published by ACM
January 2016 AI Matters: Volume 2 Issue 2, December 2015
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 8,   Downloads (12 Months): 80,   Downloads (Overall): 294

Full text available: PDFPDF
These are boom times for AI. Articles celebrating the success of AI research appear frequently in the international press. Every day, millions of people routinely use AI-based systems that the founders of the field would hail as miraculous. And there is a palpable sense of excitement about impending applications of ...

7
January 2016 Autonomous Agents and Multi-Agent Systems: Volume 30 Issue 1, January 2016
Publisher: Kluwer Academic Publishers
Bibliometrics:
Citation Count: 6

For real-world applications, virtual agents must be able to learn new behaviors from non-technical users. Positive and negative feedback are an intuitive way to train new behaviors, and existing work has presented algorithms for learning from such feedback. That work, however, treats feedback as numeric reward to be maximized, and ...
Keywords: Learning from feedback, Human---computer interaction, Interactive learning, Machine learning, Bayesian inference, Reinforcement learning

8
July 2015 IJCAI'15: Proceedings of the 24th International Conference on Artificial Intelligence
Publisher: AAAI Press
Bibliometrics:
Citation Count: 0

Research in learning from demonstration can generally be grouped into either imitation learning or intention learning. In imitation learning, the goal is to imitate the observed behavior of an expert and is typically achieved using supervised learning techniques. In intention learning, the goal is to learn the intention that motivated ...

9
July 2014 AAAI'14: Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence
Publisher: AAAI Press
Bibliometrics:
Citation Count: 0

This paper introduces two novel algorithms for learning behaviors from human-provided rewards. The primary novelty of these algorithms is that instead of treating the feedback as a numeric reward signal, they interpret feedback as a form of discrete communication that depends on both the behavior the trainer is trying to ...

10 published by ACM
April 2014 CHI '14: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Publisher: ACM
Bibliometrics:
Citation Count: 59
Downloads (6 Weeks): 25,   Downloads (12 Months): 232,   Downloads (Overall): 1,208

Full text available: PDFPDF
We investigate the practicality of letting average users customize smart-home devices using trigger-action ("if, then") programming. We find trigger-action programming can express most desired behaviors submitted by participants in an online study. We identify a class of triggers requiring machine learning that has received little attention. We evaluate the uniqueness ...
Keywords: condition-action programming, end-user programming, home automation, internet of things, smart home

11
July 2013 AAAI'13: Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence
Publisher: AAAI Press
Bibliometrics:
Citation Count: 9

We focus on effective sample-based planning in the face of underactuation, high-dimensionality, drift, discrete system changes, and stochasticity. These are hallmark challenges for important problems, such as humanoid locomotion. In order to ensure broad applicability, we assume domain expertise is minimal and limited to a generative model. In order to ...

12
June 2013 ICML'13: Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28
Publisher: JMLR.org
Bibliometrics:
Citation Count: 2

Cross-entropy optimization (CE) has proven to be a powerful tool for search in control environments. In the basic scheme, a distribution over proposed solutions is repeatedly adapted by evaluating a sample of solutions and refocusing the distribution on a percentage of those with the highest scores. We show that, in ...

13
June 2013 ICML'13: Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28
Publisher: JMLR.org
Bibliometrics:
Citation Count: 0

COCO ("cooperative/competitive") values are a solution concept for two-player normal-form games with transferable utility, when binding agreements and side payments between players are possible. In this paper, we show that COCO values can also be defined for stochastic games and can be learned using a simple variant of Q -learning ...

14
January 2013 AAAIWS'13-17: Proceedings of the 17th AAAI Conference on Late-Breaking Developments in the Field of Artificial Intelligence
Publisher: AAAI Press
Bibliometrics:
Citation Count: 0

Reinforcement-learning (RL) algorithms are often tweaked and tuned to specific environments when applied, calling into question whether learning can truly be considered autonomous in these cases. In this work, we show how more robust learning across environments is possible by adopting an ensemble approach to reinforcement learning. Our approach learns ...

15 published by ACM
November 2012 ACM Transactions on Computation Theory (TOCT): Volume 4 Issue 4, November 2012
Publisher: ACM
Bibliometrics:
Citation Count: 5
Downloads (6 Weeks): 3,   Downloads (12 Months): 17,   Downloads (Overall): 153

Full text available: PDFPDF
We show that the problem of finding an optimal stochastic blind controller in a Markov decision process is an NP-hard problem. The corresponding decision problem is NP-hard in PSPACE and sqrt-sum -hard, hence placing it in NP would imply breakthroughs in long-standing open problems in computer science. Our result establishes ...
Keywords: computational complexity, computations on polynomials, stochastic controller, Motzkin-Straus theorem, Partially observable Markov decision process, bilinear program, matrix fractional program, nonlinear optimization, sum-of-square-roots problem

16
January 2010 AAAIWS'10-09: Proceedings of the 9th AAAI Conference on Enabling Intelligence Through Middleware
Publisher: AAAI Press
Bibliometrics:
Citation Count: 0




The ACM Digital Library is published by the Association for Computing Machinery. Copyright © 2018 ACM, Inc.
Terms of Usage   Privacy Policy   Code of Ethics   Contact Us