Tensor Decomposition for Multi-agent Predictive State Representation
This addresses the problem of multi-agent planning for researchers in AI and robotics, though it is incremental as it extends single-agent PSR to multi-agent settings using existing tensor methods.
The paper tackles the challenge of learning multi-agent predictive state representation (PSR) models, which had no prior work, by using tensor decomposition techniques to handle system dynamics and derive parameters, showing that the methods effectively solve multi-agent PSR modeling problems in multiple domains.
Predictive state representation~(PSR) uses a vector of action-observation sequence to represent the system dynamics and subsequently predicts the probability of future events. It is a concise knowledge representation that is well studied in a single-agent planning problem domain. To the best of our knowledge, there is no existing work on using PSR to solve multi-agent planning problems. Learning a multi-agent PSR model is quite difficult especially with the increasing number of agents, not to mention the complexity of a problem domain. In this paper, we resort to tensor techniques to tackle the challenging task of multi-agent PSR model development problems. By first focusing on a two-agent setting, we construct the system dynamics matrix as a high order tensor for a PSR model, learn the prediction parameters and deduce state vectors directly through two different tensor decomposition methods respectively, and derive the transition parameters via linear regression. Subsequently, we generalize the PSR learning approaches in a multi-agent setting. Experimental results show that our methods can effectively solve multi-agent PSR modelling problems in multiple problem domains.