Deep Sets for Generalization in RL
This paper investigates the idea of encoding object-centered representations in the design of the reward function and policy architectures of a language-guided reinforcement learning agent. This is done using a combination of object-wise permutation invariant networks inspired from Deep Sets and gated-attention mechanisms. In a 2D procedurally-generated world where agents targeting goals in natural language navigate and interact with objects, we show that these architectures demonstrate strong generalization capacities to out-of-distribution goals. We study the generalization to varying numbers of objects at test time and further extend the object-centered architectures to goals involving relational reasoning.
Code (0)
등록된 구현이 없습니다.
Tasks
NavigateObjectreinforcement-learningReinforcement LearningReinforcement Learning (RL)Relational ReasoningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
In this paper we propose to study generalization of neural networks on small algorithmically generated datasets. In this setting, questions about data efficiency, memorization, generalization, and speed of learning can b…
MemorizationIn Search of Forgotten Domain Generalization
Out-of-Domain (OOD) generalization is the ability of a model trained on one or more domains to generalize to unseen domains. In the ImageNet era of computer vision, evaluation sets for measuring a model's OOD performance…
Domain GeneralizationDatasets for Studying Generalization from Easy to Hard Examples
We describe new datasets for studying generalization from easy to hard examples.
In Search of Lost Domain Generalization
The goal of domain generalization algorithms is to predict well on distributions different from those seen during training. While a myriad of domain generalization algorithms exist, inconsistencies in experimental condit…
Domain GeneralizationModel SelectionDomain Adversarial Active Learning for Domain Generalization Classification
Domain generalization models aim to learn cross-domain knowledge from source domain data, to improve performance on unknown target domains. Recent research has demonstrated that diverse and rich source domain samples can…
Active LearningClassificationDomain Generalization