Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making

Vivek Myers; Chongyi Zheng; Anca Dragan; Sergey Levine; Benjamin Eysenbach

2024 ICML ICML 2024

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning

Authors

Vivek Myers, Chongyi Zheng, Anca Dragan, Sergey Levine, Benjamin Eysenbach

Topics

Artificial Intelligence > Core AI > Planning Machine Learning > Core Methods > Representation Learning Reinforcement Learning > Methods > Deep RL

Keywords

contrastive learning successor feature stochastic setting triangle inequality temporal distance quasimetrics

Download PDF