Paper
Publication
Active offline policy selection
Paper
Publication
ParK: Sound and Efficient Kernel Ridge Regression by Feature Space Partitions
Paper
Publication
Is Bang-Bang Control All You Need?
Paper
Publication
On the Expressivity of Markov Reward
Paper
Publication
Which priors matter? Benchmarking models for learning latent dynamics
Paper
Publication
SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision
Paper
Publication
The Difficulty of Passive Learning in Deep Reinforcement Learning
Paper
Publication
Entropy-based adaptive Hamiltonian Monte Carlo
Paper
Publication
Overcoming the Convex Barrier for Simplex Inputs
Paper
Publication
Asymptotically Best Casual Effect Identification with Multi-Armed Bandits
Paper
Publication
How to transfer algorithmic reasoning knowledge to learn new algorithms?
Paper
Publication
Self-Consistent Models and Values
Paper
Publication
Towards mental time travel: a hierarchical memory for reinforcement learning agents
Paper
Publication
Powerpropagation: A sparsity inducing weight reparameterisation
Paper
Publication
Temporally Abstract Partial Models
Paper
Publication
Drop, Swap, and Generate: A Self-SupervisedApproach for Disentangling Neural Activity
Paper
Publication
No Regrets for Learning the Prior in Bandits
Paper
Publication
A Provably Efficient Sample Collection Strategy for Reinforcement Learning
Paper
Publication
Multimodal Few-Shot Learning with Frozen Language Models
Paper
Publication
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Paper
Publication
Laplace Redux -- Effortless Bayesian Deep Learning
Paper
Publication
On the Role of Optimization in Double Descent: A Least Squares Study
Paper
Publication
Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel
Paper
Publication
Unifying gradient estimators for meta-reinforcement learning via off-policy evaluation
Paper
Publication
The functional specialization of visual cortex emerges from training parallel pathways with self-supervised predictive learning