Search for: All records

In many real‐world applications of AI, the set of actors and tasks are not constant, but instead change over time. Robots tasked with suppressing wildfires eventually run out of limited suppressant resources and need to temporarily disengage from the collaborative work in order to recharge, or they might become damaged and leave the environment permanently. In a large business organization, objectives and goals change with the market, requiring workers to adapt to perform different sets of tasks across time. We call these multiagent systems (MAS)open agent systems(OASYS), and theopennessof the sets of agents and tasks necessitates new capabilities and modeling for decision making compared to planning and learning inclosedenvironments. In this article, we discuss three notions of openness: agent openness, task openness, and type openness. We also review the past and current research on addressing the novel challenges brought about by openness in OASYS. We share lessons learned from these efforts and suggest directions for promising future work in this area. We also encourage the community to engage and participate in this area of MAS research to address critical real‐world problems in the application of AI to enhance our daily lives.

 

In open multiagent systems, the set of agents operating in the environment changes over time and in ways that are nontrivial to predict. For example, if collaborative robots were tasked with fighting wildfires, they may run out of suppressants and be temporarily unavailable to assist their peers. Because an agent's optimal action depends on the actions of others, each agent must not only predict the actions of its peers, but, before that, reason whether they are even present to perform an action. Addressing openness thus requires agents to model each other’s presence, which can be enhanced through agents communicating about their presence in the environment. At the same time, communicative acts can also incur costs (e.g., consuming limited bandwidth), and thus an agent must tradeoff the benefits of enhanced coordination with the costs of communication. We present a new principled, decision-theoretic method in the context provided by the recent communicative interactive POMDP framework for planning in open agent settings that balances this tradeoff. Simulations of multiagent wildfire suppression problems demonstrate how communication can improve planning in open agent environments, as well as how agents tradeoff the benefits and costs of communication under different scenarios. 

Multi-task IRL recognizes that expert(s) could be switching between multiple ways of solving the same problem, or interleaving demonstrations of multiple tasks. The learner aims to learn the reward functions that individually guide these distinct ways. We present a new method for multi-task IRL that generalizes the well-known maximum entropy approach by combining it with a Dirichlet process based minimum entropy clustering of the observed data. This yields a single nonlinear optimization problem, called MinMaxEnt Multi-task IRL (MME-MTIRL), which can be solved using the Lagrangian relaxation and gradient descent methods. We evaluate MME- MTIRL on the robotic task of sorting onions on a processing line where the expert utilizes multiple ways of detecting and removing blemished onions. The method is able to learn the underlying reward functions to a high level of accuracy and it improves on the previous approaches. 

The sum-product network (SPN) has been extended to model sequence data with the recurrent SPN (RSPN), and to decision-making problems with sum-product-max networks (SPMN). In this paper, we build on the concepts introduced by these extensions and present state-based recurrent SPMNs (S-RSPMNs) as a generalization of SPMNs to sequential decision-making problems where the state may not be perfectly observed. As with recurrent SPNs, S-RSPMNs utilize a repeatable template network to model sequences of arbitrary lengths. We present an algorithm for learning compact template structures by identifying unique belief states and the transitions between them through a state matching process that utilizes augmented data. In our knowledge, this is the first data-driven approach that learns graphical models for planning under partial observability, which can be solved efficiently. S-RSPMNs retain the linear solution complexity of SPMNs, and we demonstrate significant improvements in compactness of representation and the run time of structure learning and inference in sequential domains.

 

Sum-product networks (SPN) are knowledge compilation models and are related to other graphical models for efficient probabilistic inference such as arithmetic circuits and AND/OR graphs. Recent investigations into generalizing SPNs have yielded sum-product-max networks (SPMN) which offer a data-driven alternative for decision making that has predominantly relied on handcrafted models. However, SPMNs are not suited for decision-theoretic planning which involves sequential decision making over multiple time steps. In this paper, we present recurrent SPMNs (RSPMN) that learn from and model decision-making data over time. RSPMNs utilize a template network that is unfolded as needed depending on the length of the data sequence. This is significant as RSPMNs not only inherit the benefits of SPNs in being data driven and mostly tractable, they are also well suited for planning problems. We establish soundness conditions on the template network, which guarantee that the resulting SPMN is valid, and present a structure learning algorithm to learn a sound template. RSPMNs learned on a testbed of data sets, some generated using RDDLSim, yield MEUs and policies that are close to the optimal on perfectly-observed domains and easily improve on a recent batch-constrained RL method, which is important because RSPMNs offer a new model-based approach to offline RL.