Paper
Publication
Universal Agent Mixtures and the Geometry of Intelligence
Paper
Publication
Learnable Commutative Monoids for Graph Neural Networks
Paper
Publication
Towards combinatorial invariance for Kazhdan-Lusztig polynomials
Paper
Publication
Testing Independence of Exchangeable Random Variables
Paper
Publication
Beyond Bayes-optimality: meta-learning what you know you don’t know
Paper
Publication
Game Theoretic Rating in n-player general-sum games with Equilibria
Paper
Publication
Optimistic posterior sampling for reinforcement learning with few samples and tight guarantees
Paper
Publication
Reinforcement Learning with Information Theoretic Actuation
Paper
Publication
Generalised Policy Improvement with Geometric Policy Composition
Paper
Publication
From Dirichlet to Rubin: Optimistic exploration in RL without bonuses
Paper
Publication
Scaling Gaussian process optimization by evaluating a few unique candidates multiple times
Paper
Publication
Uniqueness and Complexity of Inverse MDP Models
Paper
Publication
Graph Neural Networks are Dynamic Programmers
Paper
Publication
An adaptive and efficient multi-goal exploration
Paper
Publication
Marginalized operators for off-policy reinforcement learning
Paper
Publication
Your Policy Regularizer is Secretly an Adversary
Paper
Publication
Sample-based Approximation of Nash in Large Many-Player Games via Gradient Descent
Paper
Publication
Reward-Punishment Symmetric Universal Intelligence
Paper
Publication
Learning Optimal Conformal Classifiers
Paper
Publication
Feature and Parameter Selection in Stochastic Linear Bandits
Paper
Publication
On the Role of Neural Collapse in Transfer Learning
Paper
Publication
ParK: Sound and Efficient Kernel Ridge Regression by Feature Space Partitions
Paper
Publication
On the Expressivity of Markov Reward
Paper
Publication
Asymptotically Best Casual Effect Identification with Multi-Armed Bandits
Paper
Publication
Statistical discrimination in learning agents