Assistant Agents for Sequential Planning Problems

Association for the Advancement of Artificial Intelligence 2016-01-05T19:29:20Z 2016-01-05T19:29:20Z 2012-10

The problem of optimal planning under uncertainty in collaborative multi-agent domains is known to be deeply intractable but still demands a solution. This thesis will explore principled approximation methods that yield tractable approaches to planning for AI assistants, which allow them to understand the intentions of humans and help them achieve their goals. AI assistants are ubiquitous in video games, mak- ing them attractive domains for applying these planning techniques. However, games are also challenging domains, typically having very large state spaces and long planning horizons. The approaches in this thesis will leverage recent advances in Monte-Carlo search, approximation of stochastic dynamics by deterministic dynamics, and hierarchical action representation, to handle domains that are too complex for existing state of the art planners. These planning techniques will be demonstrated across a range of video game domains.

Article; http://purl.org/eprint/type/ConferencePaper

Open access content. Open access content
Creative Commons Attribution-Noncommercial-Share Alike
http://creativecommons.org/licenses/by-nc-sa/4.0

application/pdf
en_US

MYG oai:dspace.mit.edu:1721.1/100703
Macindoe, Owen. "Assistant Agents for Sequential Planning Problems." 8th Artificial Intelligence and Interactive Digital Entertainment Conference (October 2012).
1141879464

MASSACHUSETTS INST OF TECHNOL LIBRS
From OAIster®, provided by the OCLC Cooperative.

edsoai.on1141879464