A Unifying Framework for Observer-Aware Planning and its Complexity
Shuwa Miura, Shlomo Zilberstein · Uncertainty in Artificial Intelligence · 2021
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 is very hard to solve. Hence, we introduce a more efficient framework for producing observer-aware behaviors called Observer-Aware MDP (OAMDP) and analyze its relationship to I-POMDP. We illustrate that OAMDPs can be used to improve interpretability of agent behaviors in several scenarios and establish complexity results for OAMDPs.