A major challenge in aligning large language models (LLMs) with human preferences is the issue of distribution shift. LLM alignment algorithms rely on static preference datasets, assuming that they accurately represent real-world user preferences. However, user preferences vary significantly across geographical regions, demographics, linguistic patterns, and evolving cultural trends. This preference distribution shift leads to catastrophic alignment failures in many real-world applications. We address this problem using the principled framework of distributionally robust optimization, and develop two novel distributionally robust direct preference optimization (DPO) algorithms, namely, Wasserstein DPO (WDPO) and Kullback-Leibler DPO (KLDPO). We characterize the sample complexity of learning the optimal policy parameters for WDPO and KLDPO. Moreover, we propose scalable gradient descent-style learning algorithms by developing suitable approximations for the challenging minimax loss functions of WDPO and KLDPO. Our empirical experiments demonstrate the superior performance of WDPO and KLDPO in substantially improving the alignment when there is a preference distribution shift.

We address the problem of best policy identification in preference-based reinforcement learning (PbRL), where learning occurs from noisy binary preferences over trajectory pairs rather than explicit numerical rewards. This approach is useful for post-training optimization of generative AI models during multi-turn user interactions, where preference feedback is more robust than handcrafted reward models. In this setting, learning is driven by both an offline preference dataset -- collected from a rater of unknown 'competence' -- and online data collected with pure exploration. Since offline datasets may exhibit out-of-distribution (OOD) biases, principled online data collection is necessary. To address this, we propose Posterior Sampling for Preference Learning ($\mathsf{PSPL}$), a novel algorithm inspired by Top-Two Thompson Sampling, that maintains independent posteriors over the true reward model and transition dynamics. We provide the first theoretical guarantees for PbRL in this setting, establishing an upper bound on the simple Bayesian regret of $\mathsf{PSPL}$. Since the exact algorithm can be computationally impractical, we also provide an approximate version that outperforms existing baselines.

In this paper, we present the $\texttt{e-COP}$ algorithm, the first policy optimization algorithm for constrained Reinforcement Learning (RL) in episodic (finite horizon) settings. Such formulations are applicable when there are separate sets of optimization criteria and constraints on a system's behavior. We approach this problem by first establishing a policy difference lemma for the episodic setting, which provides the theoretical foundation for the algorithm. Then, we propose to combine a set of established and novel solution ideas to yield the $\texttt{e-COP}$ algorithm that is easy to implement and numerically stable, and provide a theoretical guarantee on optimality under certain scaling assumptions. Through extensive empirical analysis using benchmarks in the Safety Gym suite, we show that our algorithm has similar or better performance than SoTA (non-episodic) algorithms adapted for the episodic setting. The scalability of the algorithm opens the door to its application in safety-constrained Reinforcement Learning from Human Feedback for Large Language or Diffusion Models.

In this paper, we introduce the constrained best mixed arm identification (CBMAI) problem with a fixed budget. This is a pure exploration problem in a stochastic finite armed bandit model. Each arm is associated with a reward and multiple types of costs from unknown distributions. Unlike the unconstrained best arm identification problem, the optimal solution for the CBMAI problem may be a randomized mixture of multiple arms. The goal thus is to find the best mixed arm that maximizes the expected reward subject to constraints on the expected costs with a given learning budget $N$. We propose a novel, parameter-free algorithm, called the Score Function-based Successive Reject (SFSR) algorithm, that combines the classical successive reject framework with a novel score-function-based rejection criteria based on linear programming theory to identify the optimal support. We provide a theoretical upper bound on the mis-identification (of the the support of the best mixed arm) probability and show that it decays exponentially in the budget $N$ and some constants that characterize the hardness of the problem instance. We also develop an information theoretic lower bound on the error probability that shows that these constants appropriately characterize the problem difficulty. We validate this empirically on a number of average and hard instances.

In this paper, we propose Posterior Sampling Reinforcement Learning for Zero-sum Stochastic Games (PSRL-ZSG), the first online learning algorithm that achieves Bayesian regret bound of $O(HS\sqrt{AT})$ in the infinite-horizon zero-sum stochastic games with average-reward criterion. Here $H$ is an upper bound on the span of the bias function, $S$ is the number of states, $A$ is the number of joint actions and $T$ is the horizon. We consider the online setting where the opponent can not be controlled and can take any arbitrary time-adaptive history-dependent strategy. Our regret bound improves on the best existing regret bound of $O(\sqrt[3]{DS^2AT^2})$ by Wei et al. (2017) under the same assumption and matches the theoretical lower bound in $T$.

In this paper, we study the problem of efficient online reinforcement learning in the infinite horizon setting when there is an offline dataset to start with. We assume that the offline dataset is generated by an expert but with unknown level of competence, i.e., it is not perfect and not necessarily using the optimal policy. We show that if the learning agent models the behavioral policy (parameterized by a competence parameter) used by the expert, it can do substantially better in terms of minimizing cumulative regret, than if it doesn't do that. We establish an upper bound on regret of the exact informed PSRL algorithm that scales as $\tilde{O}(\sqrt{T})$. This requires a novel prior-dependent regret analysis of Bayesian online learning algorithms for the infinite horizon setting. We then propose an approximate Informed RLSVI algorithm that we can interpret as performing imitation learning with the offline dataset, and then performing online learning.

Compared to Markov Decision Processes (MDPs), learning in Partially Observable Markov Decision Processes (POMDPs) can be significantly harder due to the difficulty of interpreting observations. In this paper, we consider episodic learning problems in POMDPs with unknown transition and observation models. We consider the Posterior Sampling-based Reinforcement Learning (PSRL) algorithm for POMDPs and show that its Bayesian regret scales as the square root of the number of episodes. In general, the regret scales exponentially with the horizon length $H$, and we show that this is inevitable by providing a lower bound. However, under the condition that the POMDP is undercomplete and weakly revealing, we establish a polynomial Bayesian regret bound that improves the regret bound by a factor of $\Omega(H^2\sqrt{SA})$ over the recent result by arXiv:2204.08967.

Type 2 diabetes mellitus represents a prevalent and widespread global health concern, necessitating a comprehensive assessment of its risk factors. This study aimed towards learning whether there is any differential impact of age, Lifestyle, BMI and Waist to height ratio on the risk of Type 2 diabetes mellitus in males and females in Kolkata, West Bengal, India based on a sample observed from the out-patient consultation department of Belle Vue Clinic in Kolkata. Various machine learning models like Logistic Regression, Random Forest, and Support Vector Classifier, were used to predict the risk of diabetes, and performance was compared based on different predictors. Our findings indicate a significant age-related increase in risk of diabetes for both males and females. Although exercising and BMI was found to have significant impact on the risk of Type 2 diabetes in males, in females both turned out to be statistically insignificant. For both males and females, predictive models based on WhtR demonstrated superior performance in risk assessment compared to those based on BMI. This study sheds light on the gender-specific differences in the risk factors for Type 2 diabetes, offering valuable insights that can be used towards more targeted healthcare interventions and public health strategies.

In many branches of engineering, Banach contraction mapping theorem is employed to establish the convergence of certain deterministic algorithms. Randomized versions of these algorithms have been developed that have proved useful in data-driven problems. In a class of randomized algorithms, in each iteration, the contraction map is approximated with an operator that uses independent and identically distributed samples of certain random variables. This leads to iterated random operators acting on an initial point in a complete metric space, and it generates a Markov chain. In this paper, we develop a new stochastic dominance based proof technique, called probabilistic contraction analysis, for establishing the convergence in probability of Markov chains generated by such iterated random operators in certain limiting regime. The methods developed in this paper provides a general framework for understanding convergence of a wide variety of Monte Carlo methods in which contractive property is present. We apply the convergence result to conclude the convergence of fitted value iteration and fitted relative value iteration in continuous state and continuous action Markov decision problems as representative applications of the general framework developed here.

Over the past decade, neural network (NN)-based controllers have demonstrated remarkable efficacy in a variety of decision-making tasks. However, their black-box nature and the risk of unexpected behaviors and surprising results pose a challenge to their deployment in real-world systems with strong guarantees of correctness and safety. We address these limitations by investigating the transformation of NN-based controllers into equivalent soft decision tree (SDT)-based controllers and its impact on verifiability. Differently from previous approaches, we focus on discrete-output NN controllers including rectified linear unit (ReLU) activation functions as well as argmax operations. We then devise an exact but cost-effective transformation algorithm, in that it can automatically prune redundant branches. We evaluate our approach using two benchmarks from the OpenAI Gym environment. Our results indicate that the SDT transformation can benefit formal verification, showing runtime improvements of up to 21x and 2x for MountainCar-v0 and CartPole-v0, respectively.