Organizational Unit:
Undergraduate Research Opportunities Program

Permanent Link
https://hdl.handle.net/1853/70802
Research Organization Registry ID
Description
Previous Names
Parent Organization
Parent Organization
Organizational Unit
Includes Organization(s)
ArchiveSpace Name Record
https://finding-aids.library.gatech.edu/agents/corporate_entities/1180

Filters
2018 1
1
1
1
1
Reset filters

Settings
search.filters.applied.f.advisor: Isbell, Charles L. × Author: Kumar, Saurabh × search.filters.applied.f.isOrgUnitOfPublicationTitle: School of Computer Science ×

Publication Search Results

Now showing 1 - 1 of 1
Thumbnail Image
Item

State Space Decomposition in Reinforcement Learning

2018-05 , Kumar, Saurabh

Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, simpler domains to more complex ones using a recurrent attention mechanism. The task is presented to the agent as an image and an instruction specifying the goal. This meta-controller guides the agent towards its goal by designing a sequence of smaller subtasks on the part of the state space within the attention, effectively decomposing it. As a baseline, we consider a setup without attention as well. Our experiments show that the meta-controller learns to create sub-goals within the attention. These results have implications for human-robot interactive applications, in which a robot can transfer skills it has learned in one task to another one and be robust to variability in its environment.

View