We present an initial proposal for modular object-oriented MDPs, an extension of OO-MDPs that abstracts complex domains that are partially observable and stochastic with multiple goals. Modes reduce the curse of dimensionality by reducing the number of attributes, objects, and actions into only the features relevant for each goal. These modes may also be used as an abstracted domain to be transferred to other modes or to another domain.

We consider an autonomous agent operating in a stochastic, partially-observable, multiagent environment, that explicitly models the other agents as probabilistic deterministic finite-state controllers (PDFCs) in order to predict their actions. We assume that such models are not given to the agent, but instead must be learned from (possibly imperfect) observations of the other agents' behavior. The agent maintains a belief over the other agents' models, that is updated via Bayesian inference. To represent this belief we place a flexible stick-breaking distribution over PDFCs, that allows the posterior to concentrate around controllers whose size is not bounded and scales with the complexity of the observed data. Since this Bayesian inference task is not analytically tractable, we devise a Markov chain Monte Carlo algorithm to approximate the posterior distribution. The agent then embeds the result of this inference into its own decision making process using the interactive POMDP framework. We show that our learning algorithm can learn agent models that are behaviorally accurate for problems of varying complexity, and that the agent's performance increases as a result.

When learning a hidden Markov model (HMM), sequential observations can often be complemented by real-valued summary response variables generated from the path of hidden states. Such settings arise in numerous domains, including many applications in biology, like motif discovery and genome annotation. In this paper, we present a flexible framework for jointly modeling both latent sequence features and the functional mapping that relates the summary response variables to the hidden state sequence. The algorithm is compatible with a rich set of mapping functions. Results show that the availability of additional continuous response variables can simultaneously improve the annotation of the sequential observations and yield good prediction performance in both synthetic data and real-world datasets.

Many solution methods for Markov Decision Processes (MDPs) exploit structure in the problem and are based on value function factorization. Especially multiagent settings, however, are known to suffer from an exponential increase in value component sizes as interactions become denser, restricting problem sizes and types that can be handled. We present an approach to mitigate this limitation for certain types of multiagent systems, exploiting a property that can be thought of as "anonymous influence" in the factored MDP. We show how representational benefits from anonymity translate into computational efficiencies, both for variable elimination in a factor graph and for the approximate linear programming solution to factored MDPs. Our methods scale to factored MDPs that were previously unsolvable, such as the control of a stochastic disease process over densely connected graphs with 50 nodes and 25 agents.

The Hierarchical Graph-Coupled Hidden Markov Model (hGCHMM) is a useful tool for tracking and predicting the spread of contagious diseases, such as influenza, by leveraging social contact data collected from individual wearable devices. However, the existing inference algorithms depend on the assumption that the infection rates are small in probability, typically close to 0. The purpose of this paper is to build a unified learning framework for latent infection state estimation for the hGCHMM, regardless of the infection rate and transition function. We derive our algorithm based on a dynamic auto-encoding variational inference scheme, thus potentially generalizing the hGCHMM to models other than those that work on highly contagious diseases. We experimentally compare our approach with previous Gibbs EM algorithms and standard variational method mean-field inference, on both semi-synthetic data and app collected epidemiological and social records.

What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background knowledge and interpret test questions, but did not improve upon an information retrieval (IR) baseline. In this paper, we describe an alternative approach that operates at three levels of representation and reasoning: information retrieval, corpus statistics, and simple inference over a semi-automatically constructed knowledge base, to achieve substantially improved results. We evaluate the methods on six years of unseen, unedited exam questions from the NY Regents Science Exam (using only non-diagram, multiple choice questions), and show that our overall system’s score is 71.3%, an improvement of 23.8% (absolute) over the MLN-based method described in previous work. We conclude with a detailed analysis, illustrating the complementary strengths of each method in the ensemble. Our datasets are being released to enable further research.

We cast the Proactive Learning (PAL) problem—Active Learning (AL) with multiple reluctant, fallible, cost-varying oracles—as a Partially Observable Markov Decision Process (POMDP). The agent selects an oracle at each time step to label a data point, while it maintains a belief over the true underlying correctness of its current dataset’s labels. The goal is to minimize labeling costs while considering the value of obtaining correct labels, thus maximizing final resultant classifier accuracy. We prove three properties that show our particular formulation leads to a structured and bounded-size set of belief points, enabling strong performance of point-based methods to solve the POMDP. Our method is compared with the original three algorithms proposed by Donmez and Carbonell and a simple baseline. We demonstrate that our approach matches or improves upon the original approach within five different oracle scenarios, each on two datasets. Finally, our algorithm provides a general, well-defined mathematical foundation to build upon.

Time-varying mixture densities occur in many scenarios, for example, the distributions of keywords that appear in publications may evolve from year to year, video frame features associated with multiple targets may evolve in a sequence. Any models that realistically cater to this phenomenon must exhibit two important properties: the underlying mixture densities must have an unknown number of mixtures, and there must be some "smoothness" constraints in place for the adjacent mixture densities. The traditional Hierarchical Dirichlet Process (HDP) may be suited to the first property, but certainly not the second. This is due to how each random measure in the lower hierarchies is sampled independent of each other and hence does not facilitate any temporal correlations. To overcome such shortcomings, we proposed a new Smoothed Hierarchical Dirichlet Process (sHDP). The key novelty of this model is that we place a temporal constraint amongst the nearby discrete measures $\{G_j\}$ in the form of symmetric Kullback-Leibler (KL) Divergence with a fixed bound $B$. Although the constraint we place only involves a single scalar value, it nonetheless allows for flexibility in the corresponding successive measures. Remarkably, it also led us to infer the model within the stick-breaking process where the traditional Beta distribution used in stick-breaking is now replaced by a new constraint calculated from $B$. We present the inference algorithm and elaborate on its solutions. Our experiment using NIPS keywords has shown the desirable effect of the model.

We address the problem of estimating the parameters of a time-homogeneous Markov chain given only noisy, aggregate data. This arises when a population of individuals behave independently according to a Markov chain, but individual sample paths cannot be observed due to limitations of the observation process or the need to protect privacy. Instead, only population-level counts of the number of individuals in each state at each time step are available. When these counts are exact, a conditional least squares (CLS) estimator is known to be consistent and asymptotically normal. We initiate the study of method of moments estimators for this problem to handle the more realistic case when observations are additionally corrupted by noise. We show that CLS can be interpreted as a simple "plug-in" method of moments estimator. However, when observations are noisy, it is not consistent because it fails to account for additional variance introduced by the noise. We develop a new, simpler method of moments estimator that bypasses this problem and is consistent under noisy observations.

Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies depend on both the stochastic system dynamics as well as the reward function, the solution of the inverse problem is significantly influenced by both. Current IRL approaches assume that if the transition model is unknown, additional samples from the system's dynamics are accessible, or the observed behavior provides enough samples of the system's dynamics to solve the inverse problem accurately. These assumptions are often not satisfied. To overcome this, we present a gradient-based IRL approach that simultaneously estimates the system's dynamics. By solving the combined optimization problem, our approach takes into account the bias of the demonstrations, which stems from the generating policy. The evaluation on a synthetic MDP and a transfer learning task shows improvements regarding the sample efficiency as well as the accuracy of the estimated reward functions and transition models.