Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Peter Dayan

Peter Dayan

Correcting Experience Replay for Multi-Agent Communication


Oct 02, 2020
Sanjeevan Ahilan, Peter Dayan

Figure 1 for Correcting Experience Replay for Multi-Agent Communication
Figure 2 for Correcting Experience Replay for Multi-Agent Communication
Figure 3 for Correcting Experience Replay for Multi-Agent Communication
Figure 4 for Correcting Experience Replay for Multi-Agent Communication

  Access Paper or Ask Questions

Static and Dynamic Values of Computation in MCTS


Feb 11, 2020
Eren Sezener, Peter Dayan

Figure 1 for Static and Dynamic Values of Computation in MCTS
Figure 2 for Static and Dynamic Values of Computation in MCTS
Figure 3 for Static and Dynamic Values of Computation in MCTS
Figure 4 for Static and Dynamic Values of Computation in MCTS

  Access Paper or Ask Questions

Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning


Jan 24, 2019
Sanjeevan Ahilan, Peter Dayan

Figure 1 for Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning
Figure 2 for Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning
Figure 3 for Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning
Figure 4 for Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning

  Access Paper or Ask Questions

Probabilistic Meta-Representations Of Neural Networks


Oct 01, 2018
Theofanis Karaletsos, Peter Dayan, Zoubin Ghahramani

Figure 1 for Probabilistic Meta-Representations Of Neural Networks
Figure 2 for Probabilistic Meta-Representations Of Neural Networks
Figure 3 for Probabilistic Meta-Representations Of Neural Networks
Figure 4 for Probabilistic Meta-Representations Of Neural Networks
* presented at UAI 2018 Uncertainty In Deep Learning Workshop (UDL AUG. 2018) 
  Access Paper or Ask Questions

Fast Parametric Learning with Activation Memorization


Mar 27, 2018
Jack W Rae, Chris Dyer, Peter Dayan, Timothy P Lillicrap

Figure 1 for Fast Parametric Learning with Activation Memorization
Figure 2 for Fast Parametric Learning with Activation Memorization
Figure 3 for Fast Parametric Learning with Activation Memorization
Figure 4 for Fast Parametric Learning with Activation Memorization

  Access Paper or Ask Questions

Formalizing Neurath's Ship: Approximate Algorithms for Online Causal Learning


May 26, 2017
Neil R. Bramley, Peter Dayan, Thomas L. Griffiths, David A. Lagnado

Figure 1 for Formalizing Neurath's Ship: Approximate Algorithms for Online Causal Learning
Figure 2 for Formalizing Neurath's Ship: Approximate Algorithms for Online Causal Learning
Figure 3 for Formalizing Neurath's Ship: Approximate Algorithms for Online Causal Learning
Figure 4 for Formalizing Neurath's Ship: Approximate Algorithms for Online Causal Learning
* Psychological Review, Vol 124(3), Apr 2017, 301-338 
  Access Paper or Ask Questions

Comparison of Maximum Likelihood and GAN-based training of Real NVPs


May 15, 2017
Ivo Danihelka, Balaji Lakshminarayanan, Benigno Uria, Daan Wierstra, Peter Dayan

Figure 1 for Comparison of Maximum Likelihood and GAN-based training of Real NVPs
Figure 2 for Comparison of Maximum Likelihood and GAN-based training of Real NVPs
Figure 3 for Comparison of Maximum Likelihood and GAN-based training of Real NVPs
Figure 4 for Comparison of Maximum Likelihood and GAN-based training of Real NVPs

  Access Paper or Ask Questions

Monte Carlo Planning method estimates planning horizons during interactive social exchange


May 26, 2015
Andreas Hula, P. Read Montague, Peter Dayan

Figure 1 for Monte Carlo Planning method estimates planning horizons during interactive social exchange
Figure 2 for Monte Carlo Planning method estimates planning horizons during interactive social exchange
Figure 3 for Monte Carlo Planning method estimates planning horizons during interactive social exchange
Figure 4 for Monte Carlo Planning method estimates planning horizons during interactive social exchange

  Access Paper or Ask Questions

Better Optimism By Bayes: Adaptive Planning with Rich Models


Feb 09, 2014
Arthur Guez, David Silver, Peter Dayan

Figure 1 for Better Optimism By Bayes: Adaptive Planning with Rich Models
Figure 2 for Better Optimism By Bayes: Adaptive Planning with Rich Models
Figure 3 for Better Optimism By Bayes: Adaptive Planning with Rich Models
Figure 4 for Better Optimism By Bayes: Adaptive Planning with Rich Models
* 11 pages, 11 figures 
  Access Paper or Ask Questions

Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search


Dec 18, 2013
Arthur Guez, David Silver, Peter Dayan

Figure 1 for Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search
Figure 2 for Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search
Figure 3 for Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search
* (2012) Advances in Neural Information Processing Systems 25, pages 1034-1042 
 * 14 pages, 7 figures, includes supplementary material. Advances in Neural Information Processing Systems (NIPS) 2012 
  Access Paper or Ask Questions