154 citations · 487 across the 15 of their papers we have counts for
15 papers
The Inner Sentiments of a Thought
Chris Gagne, Peter Dayan
Transformer-based large-scale language models (LLMs) are able to generate highly realistic text. They are duly able to express, and at least implicitly represent, a wide range of s…
Reinforcement Learning with Simple Sequence Priors
Tankred Saanum, Noémi Éltető, Peter Dayan +2
Everything else being equal, simpler models should be preferred over more complex ones. In reinforcement learning (RL), simplicity is typically quantified on an action-by-action ba…
Catastrophe, Compounding & Consistency in Choice
Chris Gagne, Peter Dayan
Conditional value-at-risk (CVaR) precisely characterizes the influence that rare, catastrophic events can exert over decisions. Such characterizations are important for both normal…
Two steps to risk sensitivity
Chris Gagne, Peter Dayan
Distributional reinforcement learning (RL) -- in which agents learn about all the possible long-term consequences of their actions, and not just the expected value -- is of great r…
Correcting Experience Replay for Multi-Agent Communication
Sanjeevan Ahilan, Peter Dayan
We consider the problem of learning to communicate using multi-agent reinforcement learning (MARL). A common approach is to learn off-policy, using data sampled from a replay buffe…
Static and Dynamic Values of Computation in MCTS
Eren Sezener, Peter Dayan
Monte-Carlo Tree Search (MCTS) is one of the most-widely used methods for planning, and has powered many recent advances in artificial intelligence. In MCTS, one typically performs…
Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning
Sanjeevan Ahilan, Peter Dayan
We investigate how reinforcement learning agents can learn to cooperate. Drawing inspiration from human societies, in which successful coordination of many individuals is often fac…
Probabilistic Meta-Representations Of Neural Networks
Theofanis Karaletsos, Peter Dayan, Zoubin Ghahramani
Existing Bayesian treatments of neural networks are typically characterized by weak prior and approximate posterior distributions according to which all the weights are drawn indep…
Fast Parametric Learning with Activation Memorization
Jack W Rae, Chris Dyer, Peter Dayan +1
Neural networks trained with backpropagation often struggle to identify classes that have been observed a small number of times. In applications where most class labels are rare, s…
Comparison of Maximum Likelihood and GAN-based training of Real NVPs
Ivo Danihelka, Balaji Lakshminarayanan, Benigno Uria +2
We train a generator by maximum likelihood and we also train the same generator architecture by Wasserstein GAN. We then compare the generated samples, exact log-probability densit…
A Model of Risk and Mental State Shifts during Social Interaction
Andreas Hula, Iris Vilares, Peter Dayan +1
Cooperation and competition between human players in repeated microeconomic games offer a powerful window onto social phenomena such as the establishment, breakdown and repair of t…
Formalizing Neurath's Ship: Approximate Algorithms for Online Causal Learning
Neil R. Bramley, Peter Dayan, Thomas L. Griffiths +1
Higher-level cognition depends on the ability to learn models of the world. We can characterize this at the computational level as a structure-learning problem with the goal of bes…
Monte Carlo Planning method estimates planning horizons during interactive social exchange
Andreas Hula, P. Read Montague, Peter Dayan
Reciprocating interactions represent a central feature of all human exchanges. They have been the target of various recent experiments, with healthy participants and psychiatric po…
Better Optimism By Bayes: Adaptive Planning with Rich Models
Arthur Guez, David Silver, Peter Dayan
The computational costs of inference and planning have confined Bayesian model-based reinforcement learning to one of two dismal fates: powerful Bayes-adaptive planning but only fo…
Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search
Arthur Guez, David Silver, Peter Dayan
Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behaviour under model uncertainty, trading off exploration and exploitation in an ide…