Accounting for the Sequential Nature of States to Learn Features for Reinforcement Learning
원문 초록
In this work, we investigate the properties of data that cause popular representation learning approaches to fail. In particular, we find that in environments where states do not significantly overlap, variational autoencoders (VAEs) fail to learn useful features. We demonstrate this failure in a simple gridworld domain, and then provide a solution in the form of metric learning. However, metric learning requires supervision in the form of a distance function, which is absent in reinforcement learning. To overcome this, we leverage the sequential nature of states in a replay buffer to approximate a distance metric and provide a weak supervision signal, under the assumption that temporally close states are also semantically similar. We modify a VAE with triplet loss and demonstrate that this approach is able to learn useful features for downstream tasks, without additional supervision, in environments where standard VAEs fail.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Are encoders able to learn landmarkers for warm-starting of Hyperparameter Optimization?
Multi-view Tensor Graph Neural Networks Through Reinforced Aggregation
Multi-modal Siamese Network for Entity Alignment
Deep Fusion Feature Representation Learning with Hard Mining Center-Triplet Loss for Person Re-identification
W2VV++: Fully Deep Learning for Ad-hoc Video Search
High-Throughput Distributed Reinforcement Learning via Adaptive Policy Synchronization
토론
이 논문과 연결된 포럼 글이 아직 없습니다.