Incorporating PGMs into a BDI Architecture

Abstract

Abstract. In this paper, we present a hybrid BDI-PGM framework, in which PGMs (Probabilistic Graphical Models) are incorporated into a BDI (belief-desire-intention) architecture. This work is motivated by the need to address the scalability and noisy sensing issues in SCADA (Supervisory Control And Data Acquisition) systems. Our approach uses the incorporated PGMs to model the uncertainty reasoning and decision making processes of agents situated in a stochastic environment. In particular, we use Bayesian networks to reason about an agent's beliefs about the environment based on its sensory observations, and select optimal plans according to the utilities of actions defined in influence diagrams. This approach takes the advantage of the scalability of the BDI architecture and the uncertainty reasoning capability of PGMs. We present a prototype of the proposed approach using a transit scenario to validate its effectiveness.

A hybrid POMDP-BDI agent architecture with online stochastic planning and plan caching

“…Although Nair and Tambe (2005) and Chen et al (2013) call their approaches hybrid, our architecture can arguably more confidently be called hybrid because of its more intimate integration of POMDP and BDI concepts.…”

A Formal Approach to Embedding First-Principles Planning in BDI Agent Systems

“…For example, [25] and [26] explore the relationships between certain components of the BDI agent architectures and those in the Markov Decision Processes (MDPs) and the Partially Observable Markov Decision Processes (POMDPs), respectively. More pragmatic approaches to the application of probabilistic planning techniques in BDI agent systems can be found in the works of [27] and [12]. Although the hybrid BDI and (PO)MDP frameworks provide good insights into the potential integration of probabilistic planning into BDI agent architectures, there is still significant work to be done in modelling and reasoning uncertainty in BDI paradigms beforehand.…”

Probabilistic Planning in AgentSpeak Using the POMDP Framework

“…In this work, we instead propose an extension based on a widely used agent-oriented programming language. Our work is based on epistemic states, similar to [8], where the concept of an epistemic state is introduced to model uncertain perceptions. Similar to their work, Boolean belief atoms (e.g.…”

“…propositional statements) can be derived from epistemic states to support further reasoning. Still, the work in [8] only focuses on MDPs, i.e. it cannot be used in the more natural setting of partially observable environments.…”