Concave Utility Reinforcement Learning with Zero-Constraint Violations

We consider the problem of tabular infinite horizon concave utility reinforcement learning (CURL) with convex constraints. Various learning applications with constraints, such as robotics, do not allow for policies that can violate constraints. To this end, we propose a model-based learning algorithm that achieves zero constraint violations. To obtain this result, we assume that the concave objective and the convex constraints have a solution interior to the set of feasible occupation measures. We then solve a tighter optimization problem to ensure that the constraints are never violated despite the imprecise model knowledge and model stochasticity. We also propose a novel Bellman error based analysis for tabular infinite-horizon setups which allows to analyse stochastic policies. Combining the Bellman error based analysis and tighter optimization equation, for $T$ interactions with the environment, we obtain a regret guarantee for objective which grows as $Tilde{O}(1/sqrt{T})$, excluding other factors.

DROP: Deep relocating option policy for optimal ride-hailing vehicle repositioning

In a ride-hailing system, an optimal relocation of vacant vehicles can significantly reduce fleet idling time and balance the supply-demand distribution, enhancing system efficiency and promoting driver satisfaction and retention. Model-free deep reinforcement learning (DRL) has been shown to dynamically learn the relocating policy by actively interacting with the intrinsic dynamics in large-scale ride-hailing systems. However, the issues of sparse reward signals and unbalanced demand and supply distribution place critical barriers in developing effective DRL models. Conventional exploration strategy (e.g., the $epsilon$-greedy) may barely work under such an environment because of dithering in low-demand regions distant from high-revenue regions. This study proposes the deep relocating option policy (DROP) that supervises vehicle agents to escape from oversupply areas and effectively relocate to potentially underserved areas. We propose to learn the Laplacian embedding of a time-expanded relocation graph, as an approximation representation of the system relocation policy. The embedding generates task-agnostic signals, which in combination with task-dependent signals, constitute the pseudo-reward function for generating DROPs. We present a hierarchical learning framework that trains a high-level relocation policy and a set of low-level DROPs. The effectiveness of our approach is demonstrated using a custom-built high-fidelity simulator with real-world trip record data. We report that DROP significantly improves baseline models with 15.7% more hourly revenue and can effectively resolve the dithering issue in low-demand areas.

On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC)

Mean field control (MFC) is an effective way to mitigate the curse of dimensionality of cooperative multi-agent reinforcement learning (MARL) problems. This work considers a collection of $N_{mathrm{pop}}$ heterogeneous agents that can be segregated into $K$ classes such that the $k$-th class contains $N_k$ homogeneous agents. We aim to prove approximation guarantees of the MARL problem for this heterogeneous system by its corresponding MFC problem. We consider three scenarios where the reward and transition dynamics of all agents are respectively taken to be functions of $(1)$ joint state and action distributions across all classes, $(2)$ individual distributions of each class, and $(3)$ marginal distributions of the entire population. We show that, in these cases, the $K$-class MARL problem can be approximated by MFC with errors given as $e_1=mathcal{O}(frac{sqrt{|mathcal{X}||mathcal{U}|}}{N_{mathrm{pop}}}sum_{k}sqrt{N_k})$, $e_2=mathcal{O}(sqrt{|mathcal{X}||mathcal{U}|}sum_{k}frac{1}{sqrt{N_k}})$ and $e_3=mathcal{O}left(sqrt{|mathcal{X}||mathcal{U}|}left[frac{A}{N_{mathrm{pop}}}sum_{kin[K]}sqrt{N_k}+frac{B}{sqrt{N_{mathrm{pop}}}}right]right)$, respectively, where $A, B$ are some constants and $|mathcal{X}|,|mathcal{U}|$ are the sizes of state and action spaces of each agent. Finally, we design a Natural Policy Gradient (NPG) based algorithm that, in the three cases stated above, can converge to an optimal MARL policy within $mathcal{O}(e_j)$ error with a sample complexity of $mathcal{O}(e_j^{-3})$, $jin{1,2,3}$, respectively.

Joint Optimization of Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm

Many engineering problems have multiple objectives, and the overall aim is to optimize a non-linear function of these objectives. In this paper, we formulate the problem of maximizing a non-linear concave function of multiple long-term objectives. A policy-gradient based model-free algorithm is proposed for the problem. To compute an estimate of the gradient, a biased estimator is proposed. The proposed algorithm is shown to achieve convergence to within an $epsilon$ of the global optima after sampling $mathcal{O}(frac{M^4sigma^2}{(1-gamma)^8epsilon^4})$ trajectories where $gamma$ is the discount factor and $M$ is the number of the agents, thus achieving the same dependence on $epsilon$ as the policy gradient algorithm for the standard reinforcement learning.

Quantum-accelerated imaging of N stars

Imaging point sources with low angular separation near or below the Rayleigh criterion is important in astronomy, e.g., in the search for habitable exoplanets near stars. However, the measurement time required to resolve stars in the sub-Rayleigh region via traditional direct imaging is usually prohibitive. Here we propose quantum-accelerated imaging (QAI) to significantly reduce the measurement time using an information-theoretic approach. QAI achieves quantum acceleration by adaptively learning optimal measurements from data to maximize Fisher information per detected photon. Our approach can be implemented experimentally by linear-projection instruments followed by a single-photon detector array. We estimate the position, brightness and the number of unknown stars $10sim100$ times faster than direct imaging with the same aperture. QAI is scalable to large number of incoherent point sources and can find widespread applicability beyond astronomy to high-speed imaging, fluorescence microscopy and efficient optical read-out of qubits.

Quantum Causal Inference in the Presence of Hidden Common Causes: an Entropic Approach

Quantum causality is an emerging field of study which has the potential to greatly advance our understanding of quantum systems. One of the most important problems in quantum causality is linked to this prominent aphorism that states correlation does not mean causation. A direct generalization of the existing causal inference techniques to the quantum domain is not possible due to superposition and entanglement. We put forth a new theoretical framework for merging quantum information science and causal inference by exploiting entropic principles. For this purpose, we leverage the concept of conditional density matrices to develop a scalable algorithmic approach for inferring causality in the presence of latent confounders (common causes) in quantum systems. We apply our proposed framework to an experimentally relevant scenario of identifying message senders on quantum noisy links, where it is validated that the input before noise as a latent confounder is the cause of the noisy outputs. We also demonstrate that the proposed approach outperforms the results of classical causal inference even when the variables are classical by exploiting quantum dependence between variables through density matrices rather than joint probability distributions. Thus, the proposed approach unifies classical and quantum causal inference in a principled way. This successful inference on a synthetic quantum dataset can lay the foundations of identifying originators of malicious activity on future multi-node quantum networks.

AdaPool: A Diurnal-Adaptive Fleet Management Framework using Model-Free Deep Reinforcement Learning and Change Point Detection

This paper introduces an adaptive model-free deep reinforcement approach that can recognize and adapt to the diurnal patterns in the ride-sharing environment with car-pooling. Deep Reinforcement Learning (RL) suffers from catastrophic forgetting due to being agnostic to the timescale of changes in the distribution of experiences. Although RL algorithms are guaranteed to converge to optimal policies in Markov decision processes (MDPs), this only holds in the presence of static environments. However, this assumption is very restrictive. In many real-world problems like ride-sharing, traffic control, etc., we are dealing with highly dynamic environments, where RL methods yield only sub-optimal decisions. To mitigate this problem in highly dynamic environments, we (1) adopt an online Dirichlet change point detection (ODCP) algorithm to detect the changes in the distribution of experiences, (2) develop a Deep Q Network (DQN) agent that is capable of recognizing diurnal patterns and making informed dispatching decisions according to the changes in the underlying environment. Rather than fixing patterns by time of week, the proposed approach automatically detects that the MDP has changed, and uses the results of the new model. In addition to the adaptation logic in dispatching, this paper also proposes a dynamic, demand-aware vehicle-passenger matching and route planning framework that dynamically generates optimal routes for each vehicle based on online demand, vehicle capacities, and locations. Evaluation on New York City Taxi public dataset shows the effectiveness of our approach in improving the fleet utilization, where less than 50% of the fleet are utilized to serve the demand of up to 90% of the requests, while maximizing profits and minimizing idle times.

Quantum Entropic Causal Inference

As quantum computing and networking nodes scale-up, important open questions arise on the causal influence of various sub-systems on the total system performance. These questions are related to the tomographic reconstruction of the macroscopic wavefunction and optimizing connectivity of large engineered qubit systems, the reliable broadcasting of information across quantum networks as well as speed-up of classical causal inference algorithms on quantum computers. A direct generalization of the existing causal inference techniques to the quantum domain is not possible due to superposition and entanglement. We put forth a new theoretical framework for merging quantum information science and causal inference by exploiting entropic principles. First, we build the fundamental connection between the celebrated quantum marginal problem and entropic causal inference. Second, inspired by the definition of geometric quantum discord, we fill the gap between classical conditional probabilities and quantum conditional density matrices. These fundamental theoretical advances are exploited to develop a scalable algorithmic approach for quantum entropic causal inference. We apply our proposed framework to an experimentally relevant scenario of identifying message senders on quantum noisy links. This successful inference on a synthetic quantum dataset can lay the foundations of identifying originators of malicious activity on future multi-node quantum networks. We unify classical and quantum causal inference in a principled way paving the way for future applications in quantum computing and networking.

Communication Efficient Parallel Reinforcement Learning

We consider the problem where $M$ agents interact with $M$ identical and independent environments with $S$ states and $A$ actions using reinforcement learning for $T$ rounds. The agents share their data with a central server to minimize their regret. We aim to find an algorithm that allows the agents to minimize the regret with infrequent communication rounds. We provide NAM which runs at each agent and prove that the total cumulative regret of $M$ agents is upper bounded as $Tilde{O}(DSsqrt{MAT})$ for a Markov Decision Process with diameter $D$, number of states $S$, and number of actions $A$. The agents synchronize after their visitations to any state-action pair exceeds a certain threshold. Using this, we obtain a bound of $Oleft(MSAlog(MT)right)$ on the total number of communications rounds. Finally, we evaluate the algorithm against multiple environments and demonstrate that the proposed algorithm performs at par with an always communication version of the UCRL2 algorithm, while with significantly lower communication.

Multi-Agent Multi-Armed Bandits with Limited Communication

We consider the problem where $N$ agents collaboratively interact with an instance of a stochastic $K$ arm bandit problem for $K gg N$. The agents aim to simultaneously minimize the cumulative regret over all the agents for a total of $T$ time steps, the number of communication rounds, and the number of bits in each communication round. We present Limited Communication Collaboration - Upper Confidence Bound (LCC-UCB), a doubling-epoch based algorithm where each agent communicates only after the end of the epoch and shares the index of the best arm it knows. With our algorithm, LCC-UCB, each agent enjoys a regret of $tilde{O}left(sqrt{({K/N}+ N)T}right)$, communicates for $O(log T)$ steps and broadcasts $O(log K)$ bits in each communication step. We extend the work to sparse graphs with maximum degree $K_G$, and diameter $D$ and propose LCC-UCB-GRAPH which enjoys a regret bound of $tilde{O}left(Dsqrt{(K/N+ K_G)DT}right)$. Finally, we empirically show that the LCC-UCB and the LCC-UCB-GRAPH algorithm perform well and outperform strategies that communicate through a central node