Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution
© 2019, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Simulators are being increasingly used to train agents before deploying them in real-world environments. While training in simulation provides a cost-effective way to learn, poorly modeled aspects...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Association for the Advancement of Artificial Intelligence (AAAI)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/137315 |
| _version_ | 1811087923928367104 |
|---|---|
| author | Ramakrishnan, Ramya Kamar, Ece Nushi, Besmira Dey, Debadeepta Shah, Julie A Horvitz, Eric |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Ramakrishnan, Ramya Kamar, Ece Nushi, Besmira Dey, Debadeepta Shah, Julie A Horvitz, Eric |
| author_sort | Ramakrishnan, Ramya |
| collection | MIT |
| description | © 2019, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Simulators are being increasingly used to train agents before deploying them in real-world environments. While training in simulation provides a cost-effective way to learn, poorly modeled aspects of the simulator can lead to costly mistakes, or blind spots. While humans can help guide an agent towards identifying these error regions, humans themselves have blind spots and noise in execution. We study how learning about blind spots of both can be used to manage hand-off decisions when humans and agents jointly act in the real-world in which neither of them are trained or evaluated fully. The formulation assumes that agent blind spots result from representational limitations in the simulation world, which leads the agent to ignore important features that are relevant for acting in the open world. Our approach for blind spot discovery combines experiences collected in simulation with limited human demonstrations. The first step applies imitation learning to demonstration data to identify important features that the human is using but that the agent is missing. The second step uses noisy labels extracted from action mismatches between the agent and the human across simulation and demonstration data to train blind spot models. We show through experiments on two domains that our approach is able to learn a succinct representation that accurately captures blind spot regions and avoids dangerous errors in the real world through transfer of control between the agent and the human. |
| first_indexed | 2024-09-23T13:54:03Z |
| format | Article |
| id | mit-1721.1/137315 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:54:03Z |
| publishDate | 2021 |
| publisher | Association for the Advancement of Artificial Intelligence (AAAI) |
| record_format | dspace |
| spelling | mit-1721.1/1373152022-10-01T17:52:10Z Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution Ramakrishnan, Ramya Kamar, Ece Nushi, Besmira Dey, Debadeepta Shah, Julie A Horvitz, Eric Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory © 2019, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Simulators are being increasingly used to train agents before deploying them in real-world environments. While training in simulation provides a cost-effective way to learn, poorly modeled aspects of the simulator can lead to costly mistakes, or blind spots. While humans can help guide an agent towards identifying these error regions, humans themselves have blind spots and noise in execution. We study how learning about blind spots of both can be used to manage hand-off decisions when humans and agents jointly act in the real-world in which neither of them are trained or evaluated fully. The formulation assumes that agent blind spots result from representational limitations in the simulation world, which leads the agent to ignore important features that are relevant for acting in the open world. Our approach for blind spot discovery combines experiences collected in simulation with limited human demonstrations. The first step applies imitation learning to demonstration data to identify important features that the human is using but that the agent is missing. The second step uses noisy labels extracted from action mismatches between the agent and the human across simulation and demonstration data to train blind spot models. We show through experiments on two domains that our approach is able to learn a succinct representation that accurately captures blind spot regions and avoids dangerous errors in the real world through transfer of control between the agent and the human. 2021-11-03T20:24:35Z 2021-11-03T20:24:35Z 2019-07 2021-05-04T13:55:34Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/137315 Ramakrishnan, Ramya, Kamar, Ece, Nushi, Besmira, Dey, Debadeepta, Shah, Julie A et al. 2019. "Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution." Proceedings of the AAAI Conference on Artificial Intelligence, 33. en http://dx.doi.org/10.1609/AAAI.V33I01.33016137 Proceedings of the AAAI Conference on Artificial Intelligence 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 | Ramakrishnan, Ramya Kamar, Ece Nushi, Besmira Dey, Debadeepta Shah, Julie A Horvitz, Eric Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution |
| title | Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution |
| title_full | Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution |
| title_fullStr | Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution |
| title_full_unstemmed | Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution |
| title_short | Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution |
| title_sort | overcoming blind spots in the real world leveraging complementary abilities for joint execution |
| url | https://hdl.handle.net/1721.1/137315 |
| work_keys_str_mv | AT ramakrishnanramya overcomingblindspotsintherealworldleveragingcomplementaryabilitiesforjointexecution AT kamarece overcomingblindspotsintherealworldleveragingcomplementaryabilitiesforjointexecution AT nushibesmira overcomingblindspotsintherealworldleveragingcomplementaryabilitiesforjointexecution AT deydebadeepta overcomingblindspotsintherealworldleveragingcomplementaryabilitiesforjointexecution AT shahjuliea overcomingblindspotsintherealworldleveragingcomplementaryabilitiesforjointexecution AT horvitzeric overcomingblindspotsintherealworldleveragingcomplementaryabilitiesforjointexecution |