Anomaly detection is critical for finding suspicious behavior in innumerable systems. We need to detect anomalies in real-time, i.e. determine if an incoming entity is anomalous or not, as soon as we receive it, to minimize the effects of malicious activities and start recovery as soon as possible. Therefore, online algorithms that can detect anomalies in a streaming manner are essential. We first propose MIDAS which uses a count-min sketch to detect anomalous edges in dynamic graphs in an online manner, using constant time and memory. We then propose two variants, MIDAS-R which incorporates temporal and spatial relations, and MIDAS-F which aims to filter away anomalous edges to prevent them from negatively affecting the internal data structures. We then extend the count-min sketch to a Higher-Order sketch to capture complex relations in graph data, and to reduce detecting suspicious dense subgraph problem to finding a dense submatrix in constant time. Using this sketch, we propose four streaming methods to detect edge and subgraph anomalies. Next, we broaden the graph setting to multi-aspect data. We propose MStream which detects explainable anomalies in multi-aspect data streams. We further propose MStream-PCA, MStream-IB, and MStream-AE to incorporate correlation between features. Finally, we consider multi-dimensional data streams with concept drift and propose MemStream. MemStream leverages the power of a denoising autoencoder to learn representations and a memory module to learn the dynamically changing trend in data without the need for labels. We prove a theoretical bound on the size of memory for effective drift handling. In addition, we allow quick retraining when the arriving stream becomes sufficiently different from the training data. Furthermore, MemStream makes use of two architecture design choices to be robust to memory poisoning.

We propose policy gradient algorithms which learn risk-sensitive policies in a reinforcement learning (RL) framework. Our proposed algorithms maximize the distortion risk measure (DRM) of the cumulative reward in an episodic Markov decision process in on-policy as well as off-policy RL settings. We derive a variant of the policy gradient theorem that caters to the DRM objective, and use this theorem in conjunction with a likelihood ratio-based gradient estimation scheme. We derive non-asymptotic bounds that establish the convergence of our proposed algorithms to an approximate stationary point of the DRM objective.

As human-robot collaboration increases in the workforce, it becomes essential for human-robot teams to coordinate efficiently and intuitively. Traditional approaches for human-robot scheduling either utilize exact methods that are intractable for large-scale problems and struggle to account for stochastic, time varying human task performance, or application-specific heuristics that require expert domain knowledge to develop. We propose a deep learning-based framework, called HybridNet, combining a heterogeneous graph-based encoder with a recurrent schedule propagator for scheduling stochastic human-robot teams under upper- and lower-bound temporal constraints. The HybridNet's encoder leverages Heterogeneous Graph Attention Networks to model the initial environment and team dynamics while accounting for the constraints. By formulating task scheduling as a sequential decision-making process, the HybridNet's recurrent neural schedule propagator leverages Long Short-Term Memory (LSTM) models to propagate forward consequences of actions to carry out fast schedule generation, removing the need to interact with the environment between every task-agent pair selection. The resulting scheduling policy network provides a computationally lightweight yet highly expressive model that is end-to-end trainable via Reinforcement Learning algorithms. We develop a virtual task scheduling environment for mixed human-robot teams in a multi-round setting, capable of modeling the stochastic learning behaviors of human workers. Experimental results showed that HybridNet outperformed other human-robot scheduling solutions across problem sizes for both deterministic and stochastic human performance, with faster runtime compared to pure-GNN-based schedulers.

Interpretability of reinforcement learning policies is essential for many real-world tasks but learning such interpretable policies is a hard problem. Particularly rule-based policies such as decision trees and rules lists are difficult to optimize due to their non-differentiability. While existing techniques can learn verifiable decision tree policies there is no guarantee that the learners generate a decision that performs optimally. In this work, we study the optimization of size-limited decision trees for Markov Decision Processes (MPDs) and propose OMDTs: Optimal MDP Decision Trees. Given a user-defined size limit and MDP formulation OMDT directly maximizes the expected discounted return for the decision tree using Mixed-Integer Linear Programming. By training optimal decision tree policies for different MDPs we empirically study the optimality gap for existing imitation learning techniques and find that they perform sub-optimally. We show that this is due to an inherent shortcoming of imitation learning, namely that complex policies cannot be represented using size-limited trees. In such cases, it is better to directly optimize the tree for expected return. While there is generally a trade-off between the performance and interpretability of machine learning models, we find that OMDTs limited to a depth of 3 often perform close to the optimal limit.

Animal navigation research posits that organisms build and maintain internal spatial representations, or maps, of their environment. We ask if machines -- specifically, artificial intelligence (AI) navigation agents -- also build implicit (or 'mental') maps. A positive answer to this question would (a) explain the surprising phenomenon in recent literature of ostensibly map-free neural-networks achieving strong performance, and (b) strengthen the evidence of mapping as a fundamental mechanism for navigation by intelligent embodied agents, whether they be biological or artificial. Unlike animal navigation, we can judiciously design the agent's perceptual system and control the learning paradigm to nullify alternative navigation mechanisms. Specifically, we train 'blind' agents -- with sensing limited to only egomotion and no other sensing of any kind -- to perform PointGoal navigation ('go to $\Delta$ x, $\Delta$ y') via reinforcement learning. Our agents are composed of navigation-agnostic components (fully-connected and recurrent neural networks), and our experimental setup provides no inductive bias towards mapping. Despite these harsh conditions, we find that blind agents are (1) surprisingly effective navigators in new environments (~95% success); (2) they utilize memory over long horizons (remembering ~1,000 steps of past experience in an episode); (3) this memory enables them to exhibit intelligent behavior (following walls, detecting collisions, taking shortcuts); (4) there is emergence of maps and collision detection neurons in the representations of the environment built by a blind agent as it navigates; and (5) the emergent maps are selective and task dependent (e.g. the agent 'forgets' exploratory detours). Overall, this paper presents no new techniques for the AI audience, but a surprising finding, an insight, and an explanation.

Multi-agent reinforcement learning (MARL) has witnessed significant progress with the development of value function factorization methods. It allows optimizing a joint action-value function through the maximization of factorized per-agent utilities due to monotonicity. In this paper, we show that in partially observable MARL problems, an agent's ordering over its own actions could impose concurrent constraints (across different states) on the representable function class, causing significant estimation error during training. We tackle this limitation and propose PAC, a new framework leveraging Assistive information generated from Counterfactual Predictions of optimal joint action selection, which enable explicit assistance to value function factorization through a novel counterfactual loss. A variational inference-based information encoding method is developed to collect and encode the counterfactual predictions from an estimated baseline. To enable decentralized execution, we also derive factorized per-agent policies inspired by a maximum-entropy MARL framework. We evaluate the proposed PAC on multi-agent predator-prey and a set of StarCraft II micromanagement tasks. Empirical results demonstrate improved results of PAC over state-of-the-art value-based and policy-based multi-agent reinforcement learning algorithms on all benchmarks.

We study reinforcement learning with linear function approximation where the transition probability and reward functions are linear with respect to a feature mapping $\boldsymbol{\phi}(s,a)$. Specifically, we consider the episodic inhomogeneous linear Markov Decision Process (MDP), and propose a novel computation-efficient algorithm, LSVI-UCB$^+$, which achieves an $\widetilde{O}(Hd\sqrt{T})$ regret bound where $H$ is the episode length, $d$ is the feature dimension, and $T$ is the number of steps. LSVI-UCB$^+$ builds on weighted ridge regression and upper confidence value iteration with a Bernstein-type exploration bonus. Our statistical results are obtained with novel analytical tools, including a new Bernstein self-normalized bound with conservatism on elliptical potentials, and refined analysis of the correction term. This is a minimax optimal algorithm for linear MDPs up to logarithmic factors, which closes the $\sqrt{Hd}$ gap between the upper bound of $\widetilde{O}(\sqrt{H^3d^3T})$ in (Jin et al., 2020) and lower bound of $\Omega(Hd\sqrt{T})$ for linear MDPs.

Background: Obstructive sleep apnea (OSA) is growing increasingly prevalent in many countries as obesity rises. Sufficient, effective treatment of OSA entails high social and financial costs for healthcare. Objective: For treatment purposes, predicting OSA patients' visit expenses for the coming year is crucial. Reliable estimates enable healthcare decision-makers to perform careful fiscal management and budget well for effective distribution of resources to hospitals. The challenges created by scarcity of high-quality patient data are exacerbated by the fact that just a third of those data from OSA patients can be used to train analytics models: only OSA patients with more than 365 days of follow-up are relevant for predicting a year's expenditures. Methods and procedures: The authors propose a method applying two Transformer models, one for augmenting the input via data from shorter visit histories and the other predicting the costs by considering both the material thus enriched and cases with more than a year's follow-up. Results: The two-model solution permits putting the limited body of OSA patient data to productive use. Relative to a single-Transformer solution using only a third of the high-quality patient data, the solution with two models improved the prediction performance's $R^{2}$ from 88.8% to 97.5%. Even using baseline models with the model-augmented data improved the $R^{2}$ considerably, from 61.6% to 81.9%. Conclusion: The proposed method makes prediction with the most of the available high-quality data by carefully exploiting details, which are not directly relevant for answering the question of the next year's likely expenditure.

Constrained Markov decision processes (CMDPs) model scenarios of sequential decision making with multiple objectives that are increasingly important in many applications. However, the model is often unknown and must be learned online while still ensuring the constraint is met, or at least the violation is bounded with time. Some recent papers have made progress on this very challenging problem but either need unsatisfactory assumptions such as knowledge of a safe policy, or have high cumulative regret. We propose the Safe PSRL (posterior sampling-based RL) algorithm that does not need such assumptions and yet performs very well, both in terms of theoretical regret bounds as well as empirically. The algorithm achieves an efficient tradeoff between exploration and exploitation by use of the posterior sampling principle, and provably suffers only bounded constraint violation by leveraging the idea of pessimism. Our approach is based on a primal-dual approach. We establish a sub-linear $\tilde{\mathcal{ O}}\left(H^{2.5} \sqrt{|\mathcal{S}|^2 |\mathcal{A}| K} \right)$ upper bound on the Bayesian reward objective regret along with a bounded, i.e., $\tilde{\mathcal{O}}\left(1\right)$ constraint violation regret over $K$ episodes for an $|\mathcal{S}|$-state, $|\mathcal{A}|$-action and horizon $H$ CMDP.

The classic Reinforcement Learning (RL) formulation concerns the maximization of a scalar reward function. More recently, convex RL has been introduced to extend the RL formulation to all the objectives that are convex functions of the state distribution induced by a policy. Notably, convex RL covers several relevant applications that do not fall into the scalar formulation, including imitation learning, risk-averse RL, and pure exploration. In classic RL, it is common to optimize an infinite trials objective, which accounts for the state distribution instead of the empirical state visitation frequencies, even though the actual number of trajectories is always finite in practice. This is theoretically sound since the infinite trials and finite trials objectives can be proved to coincide and thus lead to the same optimal policy. In this paper, we show that this hidden assumption does not hold in the convex RL setting. In particular, we show that erroneously optimizing the infinite trials objective in place of the actual finite trials one, as it is usually done, can lead to a significant approximation error. Since the finite trials setting is the default in both simulated and real-world RL, we believe shedding light on this issue will lead to better approaches and methodologies for convex RL, impacting relevant research areas such as imitation learning, risk-averse RL, and pure exploration among others.