Abstract

 
 
 Communication changes the beliefs of the listener and of the speaker. The value of a communicative act stems from the valuable belief states which result from this act. To model this we build on the Interactive POMDP (IPOMDP) framework, which extends POMDPs to allow agents to model others in multi-agent settings, and we include communication that can take place between the agents to formulate Communicative IPOMDPs (CIPOMDPs). We treat communication as a type of action and therefore, decisions regarding communicative acts are based on decision-theoretic planning using the Bellman optimality principle and value iteration, just as they are for all other rational actions. As in any form of planning, the results of actions need to be precisely specified. We use the Bayes’ theorem to derive how agents update their beliefs in CIPOMDPs; updates are due to agents’ actions, observations, messages they send to other agents, and messages they receive from others. The Bayesian decision-theoretic approach frees us from the commonly made assumption of cooperative discourse – we consider agents which are free to be dishonest while communicating and are guided only by their selfish rationality. We use a simple Tiger game to illustrate the belief update, and to show that the ability to rationally communicate allows agents to improve efficiency of their interactions.
 
 
Highlights
The idea of interacting and communicating with machines like we do with people is a very appealing one for AI and is important for its applications
Decision-theoretic planning in CIPOMDPs inherits a number of important properties from POMDPs: The belief over the interactive state space is a sufficient statistic for all histories of actions, observations and messages, the value functions are piece-wise linear and convex in the agents’ interactive beliefs, the Bellman backup operation is a contraction, and the value iteration converges
We presented a Bayesian approach to pragmatics of communicative acts and a decision-theoretic planning approach for communication and interaction by building on interactive POMDPs
Summary
The idea of interacting and communicating with machines like we do with people is a very appealing one for AI and is important for its applications. Decision-theoretic planning in CIPOMDPs inherits a number of important properties from POMDPs: The belief (i.e., probability distribution) over the interactive state space is a sufficient statistic for all histories of actions, observations and messages, the value functions are piece-wise linear and convex in the agents’ interactive beliefs, the Bellman backup operation is a contraction, and the value iteration converges.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have