Search

Your search keyword '"Sunehag, Peter"' showing total 8 results
Start Over Author "Sunehag, Peter" Topic reinforcement learning
8 results on '"Sunehag, Peter"'

2. Intelligence as Inference or Forcing Occam on the World

Author

Sunehag, Peter, Hutter, Marcus, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Kobsa, Alfred, editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Weikum, Gerhard, editor, Goebel, Randy, editor, Tanaka, Yuzuru, editor, Wahlster, Wolfgang, editor, Siekmann, Jörg, editor, Goertzel, Ben, editor, Orseau, Laurent, editor, and Snaider, Javier, editor

Published
2014
Full Text
View/download PDF

3. Learning Agents with Evolving Hypothesis Classes

Author

Sunehag, Peter, Hutter, Marcus, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Kühnberger, Kai-Uwe, editor, Rudolph, Sebastian, editor, and Wang, Pei, editor

Published
2013
Full Text
View/download PDF

4. On Ensemble Techniques for AIXI Approximation

Author

Veness, Joel, Sunehag, Peter, Hutter, Marcus, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Bach, Joscha, editor, Goertzel, Ben, editor, and Iklé, Matthew, editor

Published
2012
Full Text
View/download PDF

5. Optimistic AIXI

Author

Sunehag, Peter, Hutter, Marcus, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Bach, Joscha, editor, Goertzel, Ben, editor, and Iklé, Matthew, editor

Published
2012
Full Text
View/download PDF

6. Optimistic Agents Are Asymptotically Optimal

Author

Sunehag, Peter, Hutter, Marcus, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Thielscher, Michael, editor, and Zhang, Dongmo, editor

Published
2012
Full Text
View/download PDF

7. Sparse Kernel-SARSA(λ) with an Eligibility Trace

Author

Robards, Matthew, Sunehag, Peter, Sanner, Scott, Marthi, Bhaskara, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Gunopulos, Dimitrios, editor, Hofmann, Thomas, editor, Malerba, Donato, editor, and Vazirgiannis, Michalis, editor

Published
2011
Full Text
View/download PDF

8. Rationality, Optimism and Guarantees in General Reinforcement Learning.

Author

Sunehag, Peter and Hutter, Marcus

Subjects
*REINFORCEMENT learning, *STATISTICAL hypothesis testing, *PERFORMANCE evaluation, *AXIOMS, *MACHINE learning
Abstract

In this article, we present a top-down theoretical study of general reinforcement learning agents. We begin with rational agents with unlimited resources and then move to a setting where an agent can only maintain a limited number of hypotheses and optimizes plans over a horizon much shorter than what the agent designer actually wants. We axiomatize what is rational in such a setting in a manner that enables optimism, which is important to achieve systematic explorative behavior. Then, within the class of agents deemed rational, we achieve convergence and finite-error bounds. Such results are desirable since they imply that the agent learns well from its experiences, but the bounds do not directly guarantee good performance and can be achieved by agents doing things one should obviously not. Good performance cannot in fact be guaranteed for any agent in fully general settings. Our approach is to design agents that learn well from experience and act rationally. We introduce a framework for general reinforcement learning agents based on rationality axioms for a decision function and an hypothesis-generating function designed so as to achieve guarantees on the number errors. We will consistently use an optimistic decision function but the hypothesis-generating function needs to change depending on what is known/assumed. We investigate a number of natural situations having either a frequentist or Bayesian avor, deterministic or stochastic environments and either finite or countable hypothesis class. Further, to achieve sufficiently good bounds as to hold promise for practical success we introduce a notion of a class of environments being generated by a set of laws. None of the above has previously been done for fully general reinforcement learning environments. [ABSTRACT FROM AUTHOR]

Published
2015

Catalog

Books, media, physical & digital resources
See catalog results