Reinforcement learning (RL) algorithms often require a large number of data samples to learn a control policy. As a result, training them directly on the real-world systems is expensive and potentially dangerous.

Robust reinforcement learning (RL) is to find a policy that optimizes the worstcase performance over an uncertainty set of MDPs. In this paper, we focus on model-freerobust RL, where the uncertainty set is defined to be centering at a misspecified MDP that generates a single sample trajectory sequentially, and is assumed to beunknown.

In this study, we introduce a novel bandit framework for stochastic matching based on the Multi-nomial Logit (MNL) choice model. In our setting, $N$ agents on one side are assigned to $K$ arms on the other side, where each arm stochastically selects an agent from its assigned pool according to an unknown preference and yields a corresponding reward. The objective is to minimize regret by maximizing the cumulative revenue from successful matches across all agents. This task requires solving a combinatorial optimization problem based on estimated preferences, which is NP-hard and leads a naive approach to incur a computational cost of $O(K^N)$ per round. To address this challenge, we propose batched algorithms that limit the frequency of matching updates, thereby reducing the amortized computational cost (i.e., the average cost per round) to $O(1)$ while still achieving a regret bound of $\tilde{O}(\sqrt{T})$.

In online marketplaces, dynamic assortment selection and pricing for sequentially arriving buyers presents a challenge for online learning. Since the preferences of buyers are varying and uncertain, adaptive strategies are essential to meet their needs and maximize the effectiveness of offers. To address this problem, we investigate the application of online learning techniques for contextual assortment selection and pricing. Assortment selection involves the seller choosing a subset of items from a vast catalog to present to buyers, and dynamically assigning prices to the offered items. The overall goal is to maximize revenue over the course of repeated interactions. Dynamic assortment selection and pricing strategies are deployed in a variety of online sectors including e-commerce (e.g., Amazon), food delivery (e.g., Uber Eats), and hospitality (e.g., Airbnb). With similar systems becoming ubiquitous in our daily lives, there is a growing opportunity to deliver tailored product recommendations and pricing adjustments. Therefore, it is crucial to consider data-driven approaches that can enhance user experiences and boost profitability in today's highly competitive digital industry.

Computing high dimensional potential surfaces for molecular and materials systems is considered to be a great challenge in computational chemistry with potential impact in a range of areas including fundamental prediction of reaction rates. In this paper we design and discuss an algorithm that has similarities to large language models in generative AI and natural language processing. Specifically, we represent a molecular system as a graph which contains a set of nodes, edges, faces etc. Interactions between these sets, which represent molecular subsystems in our case, are used to construct the potential energy surface for a reasonably sized chemical system with 51 dimensions. Essentially a family of neural networks that pertain to the graph-based subsystems, get the job done for this 51 dimensional system. We then ask if this same family of lower-dimensional neural networks can be transformed to provide accurate predictions for a 186 dimensional potential surface. We find that our algorithm does provide reasonably accurate results for this larger dimensional problem with sub-kcal/mol accuracy for the higher dimensional potential surface problem.

We consider the sparse contextual bandit problem where arm feature affects reward through the inner product of sparse parameters. Recent studies have developed sparsity-agnostic algorithms based on the greedy arm selection policy. However, the analysis of these algorithms requires strong assumptions on the arm feature distribution to ensure that the greedily selected samples are sufficiently diverse; One of the most common assumptions, relaxed symmetry, imposes approximate origin-symmetry on the distribution, which cannot allow distributions that has origin-asymmetric support. In this paper, we show that the greedy algorithm is applicable to a wider range of the arm feature distributions from two aspects. Firstly, we show that a mixture distribution that has a greedy-applicable component is also greedy-applicable. Second, we propose new distribution classes, related to Gaussian mixture, discrete, and radial distribution, for which the sample diversity is guaranteed. The proposed classes can describe distributions with origin-asymmetric support and, in conjunction with the first claim, provide theoretical guarantees of the greedy policy for a very wide range of the arm feature distributions.

We consider dynamic multi-product pricing and assortment problems under an unknown demand over T periods, where in each period, the seller decides on the price for each product or the assortment of products to offer to a customer who chooses according to an unknown Multinomial Logit Model (MNL). Such problems arise in many applications, including online retail and advertising. We propose a randomized dynamic pricing policy based on a variant of the Online Newton Step algorithm (ONS) that achieves a $O(d\sqrt{T}\log(T))$ regret guarantee under an adversarial arrival model. We also present a new optimistic algorithm for the adversarial MNL contextual bandits problem, which achieves a better dependency than the state-of-the-art algorithms in a problem-dependent constant $\kappa_2$ (potentially exponentially small). Our regret upper bound scales as $\tilde{O}(d\sqrt{\kappa_2 T}+ \log(T)/\kappa_2)$, which gives a stronger bound than the existing $\tilde{O}(d\sqrt{T}/\kappa_2)$ guarantees.

The Robust Markov Decision Process (RMDP) framework focuses on designing control policies that are robust against the parameter uncertainties due to the mismatches between the simulator model and real-world settings. An RMDP problem is typically formulated as a max-min problem, where the objective is to find the policy that maximizes the value function for the worst possible model that lies in an uncertainty set around a nominal model. The standard robust dynamic programming approach requires the knowledge of the nominal model for computing the optimal robust policy. In this work, we propose a model-based reinforcement learning (RL) algorithm for learning an $\epsilon$-optimal robust policy when the nominal model is unknown. We consider three different forms of uncertainty sets, characterized by the total variation distance, chi-square divergence, and KL divergence. For each of these uncertainty sets, we give a precise characterization of the sample complexity of our proposed algorithm. In addition to the sample complexity results, we also present a formal analytical argument on the benefit of using robust policies. Finally, we demonstrate the performance of our algorithm on two benchmark problems.

We consider a dynamic assortment selection problem where the goal is to offer a sequence of assortments of cardinality at most $K$, out of $N$ items, to minimize the expected cumulative regret (loss of revenue). The feedback is given by a multinomial logit (MNL) choice model. This sequential decision making problem is studied under the MNL contextual bandit framework. The existing algorithms for MNL contexual bandit have frequentist regret guarantees as $\tilde{\mathrm{O}}(\kappa\sqrt{T})$, where $\kappa$ is an instance dependent constant. $\kappa$ could be arbitrarily large, e.g. exponentially dependent on the model parameters, causing the existing regret guarantees to be substantially loose. We propose an optimistic algorithm with a carefully designed exploration bonus term and show that it enjoys $\tilde{\mathrm{O}}(\sqrt{T})$ regret. In our bounds, the $\kappa$ factor only affects the poly-log term and not the leading term of the regret bounds.

Companies should focus on "Augmented Intelligence", digital product management, and in creating a digital twin of an organisation (DTO) for their next level of digital transformation and boost in growth, a top Gartner analyst has said. Augmented Intelligence is the step beyond Artificial Intelligence (AI), where you marry AI with human capability, Partha Iyengar, Vice President and Gartner Fellow, told IANS in a telephonic interaction. The concept refers to the implementation of AI not just as a replacement of human work through automation, but as a means to augment their abilities. "Augmented Intelligence could be applied across processes, across verticals and even across job functions," Iyengar said, adding that some organisations in India, including Indian Oil, have already started focusing on AI augmentation in a big way. Globally, Singapore is at the forefront of implementing AI augmentation, according to Iyengar.