A unifying framework for observer-aware planning and its complexity

Shuwa Miura, Shlomo Zilberstein
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, PMLR 161:610-620, 2021.

Abstract

Being aware of observers and the inferences they make about an agent’s behavior is crucial for successful multi-agent interaction. Existing works on observer-aware planning use different assumptions and techniques to produce observer-aware behaviors. We argue that observer-aware planning, in its most general form, can be modeled as an Interactive POMDP (I-POMDP), which requires complex modeling and is hard to solve. Hence, we introduce a less complex framework for producing observer-aware behaviors called Observer-Aware MDP (OAMDP) and analyze its relationship to I-POMDP. We establish the complexity of OAMDPs and show that they can improve interpretability of agent behaviors in several scenarios.

Cite this Paper

BibTeX
@InProceedings{pmlr-v161-miura21a, title = {A unifying framework for observer-aware planning and its complexity}, author = {Miura, Shuwa and Zilberstein, Shlomo}, booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence}, pages = {610--620}, year = {2021}, editor = {de Campos, Cassio and Maathuis, Marloes H.}, volume = {161}, series = {Proceedings of Machine Learning Research}, month = {27--30 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v161/miura21a/miura21a.pdf}, url = {https://proceedings.mlr.press/v161/miura21a.html}, abstract = {Being aware of observers and the inferences they make about an agent’s behavior is crucial for successful multi-agent interaction. Existing works on observer-aware planning use different assumptions and techniques to produce observer-aware behaviors. We argue that observer-aware planning, in its most general form, can be modeled as an Interactive POMDP (I-POMDP), which requires complex modeling and is hard to solve. Hence, we introduce a less complex framework for producing observer-aware behaviors called Observer-Aware MDP (OAMDP) and analyze its relationship to I-POMDP. We establish the complexity of OAMDPs and show that they can improve interpretability of agent behaviors in several scenarios.} }
Endnote
%0 Conference Paper %T A unifying framework for observer-aware planning and its complexity %A Shuwa Miura %A Shlomo Zilberstein %B Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2021 %E Cassio de Campos %E Marloes H. Maathuis %F pmlr-v161-miura21a %I PMLR %P 610--620 %U https://proceedings.mlr.press/v161/miura21a.html %V 161 %X Being aware of observers and the inferences they make about an agent’s behavior is crucial for successful multi-agent interaction. Existing works on observer-aware planning use different assumptions and techniques to produce observer-aware behaviors. We argue that observer-aware planning, in its most general form, can be modeled as an Interactive POMDP (I-POMDP), which requires complex modeling and is hard to solve. Hence, we introduce a less complex framework for producing observer-aware behaviors called Observer-Aware MDP (OAMDP) and analyze its relationship to I-POMDP. We establish the complexity of OAMDPs and show that they can improve interpretability of agent behaviors in several scenarios.
APA
Miura, S. & Zilberstein, S.. (2021). A unifying framework for observer-aware planning and its complexity. Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 161:610-620 Available from https://proceedings.mlr.press/v161/miura21a.html.

Related Material