Peter Sunehag
Peter Sunehag
Google - DeepMind
Verifierad e-postadress på
Citeras av
Citeras av
Value-decomposition networks for cooperative multi-agent learning
P Sunehag, G Lever, A Gruslys, WM Czarnecki, V Zambaldi, M Jaderberg, ...
arXiv preprint arXiv:1706.05296, 2017
Deep reinforcement learning in large discrete action spaces
G Dulac-Arnold, R Evans, H van Hasselt, P Sunehag, T Lillicrap, J Hunt, ...
arXiv preprint arXiv:1512.07679, 2015
Reinforcement learning in large discrete action spaces
G Dulac-Arnold, R Evans, P Sunehag, B Coppin
The sample-complexity of general reinforcement learning
T Lattimore, M Hutter, P Sunehag
International Conference on Machine Learning, 28-36, 2013
Wearable sensor activity analysis using semi-Markov models with a grammar
O Thomas, P Sunehag, G Dror, S Yun, S Kim, M Robards, A Smola, ...
Pervasive and Mobile Computing 6 (3), 342-350, 2010
Variable metric stochastic approximation theory
P Sunehag, J Trumpf, SVN Vishwanathan, N Schraudolph
Artificial Intelligence and Statistics, 560-566, 2009
Deep reinforcement learning with attention for slate markov decision processes with high-dimensional states and actions
P Sunehag, R Evans, G Dulac-Arnold, Y Zwols, D Visentin, B Coppin
arXiv preprint arXiv:1512.01124, 2015
Malthusian reinforcement learning
JZ Leibo, J Perolat, E Hughes, S Wheelwright, AH Marblestone, ...
arXiv preprint arXiv:1812.07019, 2018
Semi-Markov kMeans clustering and activity recognition from body-worn sensors
MW Robards, P Sunehag
2009 Ninth IEEE International Conference on Data Mining, 438-446, 2009
Consistency of feature Markov processes
P Sunehag, M Hutter
Algorithmic Learning Theory, 360-374, 2010
Adaptive context tree weighting
A O'Neill, M Hutter, W Shao, P Sunehag
2012 Data Compression Conference, 317-326, 2012
Feature reinforcement learning: state of the art
M Daswani, P Sunehag, M Hutter
Sequential decision-making with big data: papers from the AAAI-14 workshop, 2014
Optimistic agents are asymptotically optimal
P Sunehag, M Hutter
Australasian Joint Conference on Artificial Intelligence, 15-26, 2012
Context tree maximizing
P Nguyen, P Sunehag, M Hutter
Proceedings of the AAAI Conference on Artificial Intelligence 26 (1), 2012
Feature Reinforcement Learning In Practice
P Nguyen, P Sunehag, M Hutter
Arxiv preprint arXiv:1108.3614, 2011
Rationality, optimism and guarantees in general reinforcement learning
P Sunehag, M Hutter
The Journal of Machine Learning Research 16 (1), 1345-1390, 2015
(Non-) equivalence of universal priors
I Wood, P Sunehag, M Hutter
Algorithmic Probability and Friends. Bayesian Prediction and Artificial …, 2013
Axioms for rational reinforcement learning
P Sunehag, M Hutter
Algorithmic Learning Theory, 338-352, 2011
Optimistic AIXI
P Sunehag, M Hutter
International Conference on Artificial General Intelligence, 312-321, 2012
Sparse Kernel-SARSA (λ) with an eligibility trace
M Robards, P Sunehag, S Sanner, B Marthi
Machine Learning and Knowledge Discovery in Databases, 1-17, 2011
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20