EMDD-RL: faster subgoal identification with diverse density in reinforcement learning

Date

2021-1-15

Author

Sunel, Saim

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

37
views

38
downloads

Cite This

Diverse Density (DD) algorithm is a well-known multiple instance learning method, also known to be effective to automatically identify sub-goals and improve Reinforcement Learning (RL). Expectation-Maximization Diverse Density (EMDD) improves DD in terms of both speed and accuracy. This study adapts EMDD to automatically identify subgoals for RL which is shown to perform significantly faster (3 to 10 times) than its predecessor, without sacrificing solution quality. The performance of the proposed method named EMDD-RL is empirically shown via extensive experimentation, together with the discussions on the effects of EMDD hyperparameters on the results.

Subject Keywords

Subgoal identification, Expectation-Maximization Diverse Density, Diverse Density, Reinforcement Learning

URI

https://hdl.handle.net/11511/89597

Collections

Graduate School of Natural and Applied Sciences, Thesis