Timezone: »

Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing
Kaixin Wang · Kuangqi Zhou · Qixin Zhang · Jie Shao · Bryan Hooi · Jiashi Feng

Tue Jul 20 06:35 PM -- 06:40 PM (PDT) @

The Laplacian representation recently gains increasing attention for reinforcement learning as it provides succinct and informative representation for states, by taking the eigenvectors of the Laplacian matrix of the state-transition graph as state embeddings. Such representation captures the geometry of the underlying state space and is beneficial to RL tasks such as option discovery and reward shaping. To approximate the Laplacian representation in large (or even continuous) state spaces, recent works propose to minimize a spectral graph drawing objective, which however has infinitely many global minimizers other than the eigenvectors. As a result, their learned Laplacian representation may differ from the ground truth. To solve this problem, we reformulate the graph drawing objective into a generalized form and derive a new learning objective, which is proved to have eigenvectors as its unique global minimizer. It enables learning high-quality Laplacian representations that faithfully approximate the ground truth. We validate this via comprehensive experiments on a set of gridworld and continuous control environments. Moreover, we show that our learned Laplacian representations lead to more exploratory options and better reward shaping.

Author Information

Kaixin Wang (National University of Singapore)
Kuangqi Zhou (National University of Singapore)
Qixin Zhang (city university of hong kong)
Jie Shao (Fudan University)
Bryan Hooi (National University of Singapore)
Jiashi Feng (National University of Singapore)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors