Search Results for author:
Found 26 papers, 2 papers with code
Simplicity in Complexity
We find that complexity is well-explained by a simple linear model with these two features across six diverse image-sets of naturalistic scene and art images.
Predicting the Future with Simple World Models
Abstracting the dynamics of the environment with simple models can have several benefits.
The Inner Sentiments of a Thought
Transformer-based large-scale language models (LLMs) are able to generate highly realistic text.
Habits of Mind: Reusing Action Sequences for Efficient Planning
When we exercise sequences of actions, their execution becomes more fluent and precise.
Catastrophe, Compounding & Consistency in Choice
Conditional value-at-risk (CVaR) precisely characterizes the influence that rare, catastrophic events can exert over decisions.
Two steps to risk sensitivity
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 recent interest.
A Local Temporal Difference Code for Distributional Reinforcement Learning
Recent theoretical and experimental results suggest that the dopamine system implements distributional temporal difference backups, allowing learning of the entire distributions of the long-run values of states rather than just their expected values.
Correcting Experience Replay for Multi-Agent Communication
We consider the problem of learning to communicate using multi-agent reinforcement learning (MARL).
Static and Dynamic Values of Computation in MCTS
Monte-Carlo Tree Search (MCTS) is one of the most-widely used methods for planning, and has powered many recent advances in artificial intelligence.
Disentangled behavioural representations
Individual characteristics in human decision-making are often quantified by fitting a parametric cognitive model to subjects' behavior and then studying differences between them in the associated parameter space.
Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning
We investigate how reinforcement learning agents can learn to cooperate.
Integrated accounts of behavioral and neuroimaging data using flexible recurrent neural network models
One standard approach to this is model-based fMRI data analysis, in which a model is fitted to the behavioral data, i. e., a subject's choices, and then the neural data are parsed to find brain regions whose BOLD signals are related to the model's internal signals.
Probabilistic Meta-Representations Of Neural Networks
Existing Bayesian treatments of neural networks are typically characterized by weak prior and approximate posterior distributions according to which all the weights are drawn independently.
Fast Parametric Learning with Activation Memorization
Neural networks trained with backpropagation often struggle to identify classes that have been observed a small number of times.
Ranked #68 on
Language Modelling
on WikiText-103
Comparison of Maximum Likelihood and GAN-based training of Real NVPs
We train a generator by maximum likelihood and we also train the same generator architecture by Wasserstein GAN.
Formalizing Neurath's Ship: Approximate Algorithms for Online Causal Learning
Higher-level cognition depends on the ability to learn models of the world.
Monte Carlo Planning method estimates planning horizons during interactive social exchange
Reciprocating interactions represent a central feature of all human exchanges.
Bayes-Adaptive Simulation-based Search with Value Function Approximation
Bayes-adaptive planning offers a principled solution to the exploration-exploitation trade-off under model uncertainty.
Better Optimism By Bayes: Adaptive Planning with Rich Models
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 for simplistic models, or powerful, Bayesian non-parametric models but using simple, myopic planning strategies such as Thompson sampling.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
+1
Correlations strike back (again): the case of associative memory retrieval
It has long been recognised that statistical dependencies in neuronal activity need to be taken into account when decoding stimuli encoded in a neural population.
Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search
Bayesian model-based reinforcement learning is a formally elegant approach to learning optimal behaviour under model uncertainty, trading off exploration and exploitation in an ideal way.
Model-based Reinforcement Learning
reinforcement-learning
+1
Two is better than one: distinct roles for familiarity and recollection in retrieving palimpsest memories
Storing a new pattern in a palimpsest memory system comes at the cost of interfering with the memory traces of previously stored items.
Statistical Models of Linear and Nonlinear Contextual Interactions in Early Visual Processing
A central hypothesis about early visual processing is that it represents inputs in a coordinate system matched to the statistics of natural scenes.
Know Thy Neighbour: A Normative Theory of Synaptic Depression
Synapses exhibit an extraordinary degree of short-term malleability, with release probabilities and effective synaptic strengths changing markedly over multiple timescales.
Load and Attentional Bayes
Selective attention is a most intensively studied psychological phenomenon, rife with theoretical suggestions and schisms.
Bayesian Model of Behaviour in Economic Games
Classical Game Theoretic approaches that make strong rationality assumptions have difficulty modeling observed behaviour in Economic games of human subjects.
