Behavior compilation for AI in games
In order to cooperate effectively with human players, characters need to infer the tasks players are pursuing and select contextually appropriate responses. This process of parsing a serial input stream of observations to infer a hierarchical task structure is much like the process of compiling sour...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for the Advancement of Artificial Intelligence (AAAI)
2015
|
| Online Access: | http://hdl.handle.net/1721.1/100259 https://orcid.org/0000-0002-4333-7194 |
| _version_ | 1826202682959855616 |
|---|---|
| author | Orkin, Jeffrey David Smith, Tynan Roy, Deb K. |
| author2 | Massachusetts Institute of Technology. Media Laboratory |
| author_facet | Massachusetts Institute of Technology. Media Laboratory Orkin, Jeffrey David Smith, Tynan Roy, Deb K. |
| author_sort | Orkin, Jeffrey David |
| collection | MIT |
| description | In order to cooperate effectively with human players, characters need to infer the tasks players are pursuing and select contextually appropriate responses. This process of parsing a serial input stream of observations to infer a hierarchical task structure is much like the process of compiling source code. We draw an analogy between compiling source code and compiling behavior, and propose modeling the cognitive system of a character as a compiler, which tokenizes observations and infers a hierarchical task structure. An evaluation comparing automatically compiled behavior to human annotation demonstrates the potential for this approach to enable AI characters to understand the behavior and infer the tasks of human partners. |
| first_indexed | 2024-09-23T12:14:06Z |
| format | Article |
| id | mit-1721.1/100259 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:14:06Z |
| publishDate | 2015 |
| publisher | Association for the Advancement of Artificial Intelligence (AAAI) |
| record_format | dspace |
| spelling | mit-1721.1/1002592022-10-01T08:45:19Z Behavior compilation for AI in games Orkin, Jeffrey David Smith, Tynan Roy, Deb K. Massachusetts Institute of Technology. Media Laboratory Orkin, Jeffrey David Smith, Tynan Roy, Deb K. In order to cooperate effectively with human players, characters need to infer the tasks players are pursuing and select contextually appropriate responses. This process of parsing a serial input stream of observations to infer a hierarchical task structure is much like the process of compiling source code. We draw an analogy between compiling source code and compiling behavior, and propose modeling the cognitive system of a character as a compiler, which tokenizes observations and infers a hierarchical task structure. An evaluation comparing automatically compiled behavior to human annotation demonstrates the potential for this approach to enable AI characters to understand the behavior and infer the tasks of human partners. Singapore-MIT GAMBIT Game Lab 2015-12-15T15:06:46Z 2015-12-15T15:06:46Z 2010-10 Article http://purl.org/eprint/type/ConferencePaper http://hdl.handle.net/1721.1/100259 Orkin, Jeff, Tynan Smith, and Deb Roy. "Behavior compilation for AI in games." Sixth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (October 2010). https://orcid.org/0000-0002-4333-7194 en_US http://aaai.org/ocs/index.php/AIIDE/AIIDE10/paper/view/2115 Proceedings of the SixthAAAI Conference on Artificial Intelligence and Interactive Digital Entertainment Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for the Advancement of Artificial Intelligence (AAAI) MIT web domain |
| spellingShingle | Orkin, Jeffrey David Smith, Tynan Roy, Deb K. Behavior compilation for AI in games |
| title | Behavior compilation for AI in games |
| title_full | Behavior compilation for AI in games |
| title_fullStr | Behavior compilation for AI in games |
| title_full_unstemmed | Behavior compilation for AI in games |
| title_short | Behavior compilation for AI in games |
| title_sort | behavior compilation for ai in games |
| url | http://hdl.handle.net/1721.1/100259 https://orcid.org/0000-0002-4333-7194 |
| work_keys_str_mv | AT orkinjeffreydavid behaviorcompilationforaiingames AT smithtynan behaviorcompilationforaiingames AT roydebk behaviorcompilationforaiingames |