Agnieszka Słowik's repositories
NeuralFunctionModules
Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
InvarianceUnitTests
Toy datasets to evaluate algorithms for domain generalization and invariance learning.
awesome-rl
Reinforcement learning resources curated
EmergentLanguage
Repository for people who are insterested at topics related to Emergent Language
end-to-end-negotiator
Deal or No Deal? End-to-End Learning for Negotiation Dialogues
google-research
Google Research
gym
A toolkit for developing and comparing reinforcement learning algorithms.
ood-dataset-generators
Collection of scripts for generating out-of-distribution image datasets
Out-of-Distribution-Generalization.github.io
Adding the Slowik&Bottou DRO paper.
Permutation-Equivariant-Seq2Seq
Humans understand novel sentences by composing meanings and roles of core language components. In contrast, neural network models for natural language modeling fail when such compositional generalization is required. The main contribution of this paper is to hypothesize that language compositionality is a form of group-equivariance. Based on this hypothesis, we propose a set of tools for constructing equivariant sequence-to-sequence models. Throughout a variety of experiments on the SCAN tasks, we analyze the behavior of existing models under the lens of equivariance, and demonstrate that our equivariant architecture is able to achieve the type compositional generalization required in human language understanding.
PracticalSessions2020
Repository for tutorial sessions at EEML2020
PyGame-Learning-Environment
PyGame Learning Environment (PLE) -- Reinforcement Learning Environment in Python.
pytorch-maml-rl
Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch
sequential_social_dilemma_games
Repo for reproduction of sequential social dilemmas
Slowika2.github.io
A beautiful Jekyll theme for academics