Interactive Partially Observable Markov Decision Process Research Articles

IPOMDP-Net: A Deep Neural Network for Partially Observable Multi-Agent Planning Using Interactive POMDPs

This paper introduces the IPOMDP-net, a neural network architecture for multi-agent planning under partial observability. It embeds an interactive partially observable Markov decision process (I-POMDP) model and a QMDP planning algorithm that solves the model in a neural network architecture. The IPOMDP-net is fully differentiable and allows for end-to-end training. In the learning phase, we train an IPOMDP-net on various fixed and randomly generated environments in a reinforcement learning setting, assuming observable reinforcements and unknown (randomly initialized) model functions. In the planning phase, we test the trained network on new, unseen variants of the environments under the planning setting, using the trained model to plan without reinforcements. Empirical results show that our model-based IPOMDP-net outperforms the other state-of-the-art modelfree network and generalizes better to larger, unseen environments. Our approach provides a general neural computing architecture for multi-agent planning using I-POMDPs. It suggests that, in a multi-agent setting, having a model of other agents benefits our decision-making, resulting in a policy of higher quality and better generalizability.

A model of risk and mental state shifts during social interaction.

Cooperation and competition between human players in repeated microeconomic games offer a window onto social phenomena such as the establishment, breakdown and repair of trust. However, although a suitable starting point for the quantitative analysis of such games exists, namely the Interactive Partially Observable Markov Decision Process (I-POMDP), computational considerations and structural limitations have limited its application, and left unmodelled critical features of behavior in a canonical trust task. Here, we provide the first analysis of two central phenomena: a form of social risk-aversion exhibited by the player who is in control of the interaction in the game; and irritation or anger, potentially exhibited by both players. Irritation arises when partners apparently defect, and it potentially causes a precipitate breakdown in cooperation. Failing to model one’s partner’s propensity for it leads to substantial economic inefficiency. We illustrate these behaviours using evidence drawn from the play of large cohorts of healthy volunteers and patients. We show that for both cohorts, a particular subtype of player is largely responsible for the breakdown of trust, a finding which sheds new light on borderline personality disorder.

Decision-Theoretic Planning Under Anonymity in Agent Populations

We study the problem of self-interested planning under uncertainty in settings shared with more than a thousand other agents, each of which plans at its own individual level. We refer to such large numbers of agents as an agent population. The decision-theoretic formalism of interactive partially observable Markov decision process (I-POMDP) is used to model the agent's self-interested planning. The first contribution of this article is a method for drastically scaling the finitely-nested I-POMDP to certain agent populations for the first time. Our method exploits two types of structure that is often exhibited by agent populations -- anonymity and context-specific independence. We present a variant called the many-agent I-POMDP that models both these types of structure to plan efficiently under uncertainty in multiagent settings. In particular, the complexity of the belief update and solution in the many-agent I-POMDP is polynomial in the number of agents compared with the exponential growth that challenges the original framework. While exploiting structure helps mitigate the curse of many agents, the well-known curse of history that afflicts I-POMDPs continues to challenge scalability in terms of the planning horizon. The second contribution of this article is an application of the branch-and-bound scheme to reduce the exponential growth of the search tree for look ahead. For this, we introduce new fast-computing upper and lower bounds for the exact value function of the many-agent I-POMDP. This speeds up the look-ahead computations without trading off optimality, and reduces both memory and run time complexity. The third contribution is a comprehensive empirical evaluation of the methods on three new problems domains -- policing large protests, controlling traffic congestion at a busy intersection, and improving the AI for the popular Clash of Clans multiplayer game. We demonstrate the feasibility of exact self-interested planning in these large problems, and that our methods for speeding up the planning are effective. Altogether, these contributions represent a principled and significant advance toward moving self-interested planning under uncertainty to real-world applications.

Modeling and Algorithms for Multiagent Communication through Interactive Dynamic Influence Diagrams

ABSTRACTCommunication is an important resource for multiagent coordination. Interactive Dynamic Influence Diagrams (I-DIDs) have been used extensively in multiagent planning when there is uncertainty, and they are recognized graphical representations of Interactive Partially Observable Markov Decision Processes (I-POMDPs). We establish a communication model among multiple agents based on the I-DID framework. We use the AND-communication method by assuming a separate communication and action phase in each step, rather than replacing domain actions, in order that communication facilitates better domain-action selection. We use a synchronized communication type: when an agent initiates communication, all of the agent’s teammates synchronize to share their recent observations. We give a general algorithm to calculate communicative decision from a single-agent perspective by comparing expected rewards with and without communication. Finally, we use multiagent “tiger” and “concert” problems to validate the model’s effectiveness.

Monte Carlo Planning Method Estimates Planning Horizons during Interactive Social Exchange.

Reciprocating interactions represent a central feature of all human exchanges. They have been the target of various recent experiments, with healthy participants and psychiatric populations engaging as dyads in multi-round exchanges such as a repeated trust task. Behaviour in such exchanges involves complexities related to each agent’s preference for equity with their partner, beliefs about the partner’s appetite for equity, beliefs about the partner’s model of their partner, and so on. Agents may also plan different numbers of steps into the future. Providing a computationally precise account of the behaviour is an essential step towards understanding what underlies choices. A natural framework for this is that of an interactive partially observable Markov decision process (IPOMDP). However, the various complexities make IPOMDPs inordinately computationally challenging. Here, we show how to approximate the solution for the multi-round trust task using a variant of the Monte-Carlo tree search algorithm. We demonstrate that the algorithm is efficient and effective, and therefore can be used to invert observations of behavioural choices. We use generated behaviour to elucidate the richness and sophistication of interactive inference.

Individual Planning in Agent Populations: Exploiting Anonymity and Frame-Action Hypergraphs

Interactive partially observable Markov decision processes (I-POMDP) provide a formal framework for planning for a self-interested agent in multiagent settings. An agent operating in a multiagent environment must deliberate about the actions that other agents may take and the effect these actions have on the environment and the rewards it receives. Traditional I-POMDPs model this dependence on the actions of other agents using joint action and model spaces. Therefore, the solution complexity grows exponentially with the number of agents thereby complicating scalability. In this paper, we model and extend anonymity and context-specific independence — problem structures often present in agent populations — for computational gain. We empirically demonstrate the efficiency from exploiting these problem structures by solving a new multiagent problem involving more than 1,000 agents.

Decision Making in Complex Multiagent Contexts: A Tale of Two Frameworks

Decision making is a key feature of autonomous systems. It involves choosing optimally between different lines of action in various information contexts that range from perfectly knowing all aspects of the decision problem to having just partial knowledge about it. The physical context often includes other interacting autonomous systems, typically called agents. In this article, I focus on decision making in a multiagent context with partial information about the problem. Relevant research in this complex but realistic setting has converged around two complementary, general frameworks and also introduced myriad specializations on its way. I put the two frameworks, decentralized partially observable Markov decision process (Dec‐POMDP) and the interactive partially observable Markov decision process (I‐POMDP), in context and review the foundational algorithms for these frameworks, while briefly discussing the advances in their specializations. I conclude by examining the avenues that research pertaining to these frameworks is pursuing.

Towards Applying Interactive POMDPs to Real-World Adversary Modeling

We examine the suitability of using decision processes to model real-world systems of intelligent adversaries. Decision processes have long been used to study cooperative multiagent interactions, but their practical applicability to adversarial problems has received minimal study. We address the pros and cons of applying sequential decision-making in this area, using the crime of money laundering as a specific example. Motivated by case studies, we abstract out a model of the money laundering process, using the framework of interactive partially observable Markov decision processes (I-POMDPs). We address why this framework is well suited for modeling adversarial interactions. Particle filtering and value iteration are used to solve the model, with the application of different pruning and look-ahead strategies to assess the tradeoffs between solution quality and algorithmic run time. Our results show that there is a large gap in the level of realism that can currently be achieved by such decision models, largely due to computational demands that limit the size of problems that can be solved. While these results represent solutions to a simplified model of money laundering, they illustrate nonetheless the kinds of agent interactions that cannot be captured by standard approaches such as anomaly detection. This implies that I-POMDP methods may be valuable in the future, when algorithmic capabilities have further evolved.

Monte Carlo Sampling Methods for Approximating Interactive POMDPs

Partially observable Markov decision processes (POMDPs) provide a principled framework for sequential planning in uncertain single agent settings. An extension of POMDPs to multiagent settings, called interactive POMDPs (I-POMDPs), replaces POMDP belief spaces with interactive hierarchical belief systems which represent an agent’s belief about the physical world, about beliefs of other agents, and about their beliefs about others’ beliefs. This modification makes the difficulties of obtaining solutions due to complexity of the belief and policy spaces even more acute. We describe a general method for obtaining approximate solutions of I-POMDPs based on particle filtering (PF). We introduce the interactive PF, which descends the levels of the interactive belief hierarchies and samples and propagates beliefs at each level. The interactive PF is able to mitigate the belief space complexity, but it does not address the policy space complexity. To mitigate the policy space complexity – sometimes also called the curse of history – we utilize a complementary method based on sampling likely observations while building the look ahead reachability tree. While this approach does not completely address the curse of history, it beats back the curse’s impact substantially. We provide experimental results and chart future work.

Graphical models for interactive POMDPs: representations and solutions

We develop new graphical representations for the problem of sequential decision making in partially observable multiagent environments, as formalized by interactive partially observable Markov decision processes (I-POMDPs). The graphical models called interactive influence diagrams (I-IDs) and their dynamic counterparts, interactive dynamic influence diagrams (I-DIDs), seek to explicitly model the structure that is often present in real-world problems by decomposing the situation into chance and decision variables, and the dependencies between the variables. I-DIDs generalize DIDs, which may be viewed as graphical representations of POMDPs, to multiagent settings in the same way that I-POMDPs generalize POMDPs. I-DIDs may be used to compute the policy of an agent given its belief as the agent acts and observes in a setting that is populated by other interacting agents. Using several examples, we show how I-IDs and I-DIDs may be applied and demonstrate their usefulness. We also show how the models may be solved using the standard algorithms that are applicable to DIDs. Solving I-DIDs exactly involves knowing the solutions of possible models of the other agents. The space of models grows exponentially with the number of time steps. We present a method of solving I-DIDs approximately by limiting the number of other agents’ candidate models at each time step to a constant. We do this by clustering models that are likely to be behaviorally equivalent and selecting a representative set from the clusters. We discuss the error bound of the approximation technique and demonstrate its empirical performance.