Exchangeable Input Representations for Reinforcement Learning
Poor sample efficiency is a major limitation of deep reinforcement learning in many domains. This work presents an attention-based method to project neural network inputs into an efficient representation space that is invariant under changes to input ordering. We show that our proposed representation results in an input space that is a factor of $m!$ smaller for inputs of $m$ objects. We also show that our method is able to represent inputs over variable numbers of objects. Our experiments demonstrate improvements in sample efficiency for policy gradient methods on a variety of tasks. We show that our representation allows us to solve problems that are otherwise intractable when using na\"ive approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement LearningPolicy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Exchangeable Models in Meta Reinforcement Learning
One recent approach to meta reinforcement learning (meta-RL) is to integrate models for task inference with models for control. The former component is often based on recurrent neural networks, which do not directly expl…
Meta Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
Identifying latent representations or causal structures is important for good generalization and downstream task performance. However, both fields have been developed rather independently. We observe that several methods…
Representation LearningDeep de Finetti: Recovering Topic Distributions from Large Language Models
Large language models (LLMs) can produce long, coherent passages of text, suggesting that LLMs, although trained on next-word prediction, must represent the latent structure that characterizes a document. Prior work has …
Bayesian InferenceObject-Centric Learning with Slot Attention
Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed represe…
ObjectObject DiscoveryProperty PredictionStructure Mapping for Transferability of Causal Models
Human beings learn causal models and constantly use them to transfer knowledge between similar environments. We use this intuition to design a transfer-learning framework using object-oriented representations to learn th…
reinforcement-learningReinforcement Learning (RL)Transfer Learning