Partially observable Markov decision processes (POMDPs) are a general mathematical model for sequential decision-making in stochastic environments under state uncertainty. POMDPs are often solved \textit{online}, which enables the algorithm to adapt to new information in real time. Online solvers typically use bootstrap particle filters based on importance resampling for updating the belief distribution. Since directly sampling from the ideal state distribution given the latest observation and previous state is infeasible, particle filters approximate the posterior belief distribution by propagating states and adjusting weights through prediction and resampling steps. However, in practice, the importance resampling technique often leads to particle degeneracy and sample impoverishment when the state transition model poorly aligns with the posterior belief distribution, especially when the received observation is highly informative. We propose an approach that constructs a sequence of bridge distributions between the state-transition and optimal distributions through iterative Monte Carlo steps, better accommodating noisy observations in online POMDP solvers. Our algorithm demonstrates significantly superior performance compared to state-of-the-art methods when evaluated across multiple challenging POMDP domains.

Langevin algorithms are popular Markov chain Monte Carlo methods that are often used to solve high-dimensional large-scale sampling problems in machine learning. The most classical Langevin Monte Carlo algorithm is based on the overdamped Langevin dynamics. There are many variants of Langevin dynamics that often show superior performance in practice. In this paper, we provide a unified approach to study the acceleration of the variants of the overdamped Langevin dynamics through the lens of large deviations theory. Numerical experiments using both synthetic and real data are provided to illustrate the efficiency of these variants.

Offline reinforcement learning (RL) aims to learn from historical data without requiring (costly) access to the environment. To facilitate offline RL research, we previously introduced NeoRL, which highlighted that datasets from real-world tasks are often conservative and limited. With years of experience applying offline RL to various domains, we have identified additional real-world challenges. These include extremely conservative data distributions produced by deployed control systems, delayed action effects caused by high-latency transitions, external factors arising from the uncontrollable variance of transitions, and global safety constraints that are difficult to evaluate during the decision-making process. These challenges are underrepresented in previous benchmarks but frequently occur in real-world tasks. To address this, we constructed the extended Near Real-World Offline RL Benchmark (NeoRL-2), which consists of 7 datasets from 7 simulated tasks along with their corresponding evaluation simulators. Benchmarking results from state-of-the-art offline RL approaches demonstrate that current methods often struggle to outperform the data-collection behavior policy, highlighting the need for more effective methods. We hope NeoRL-2 will accelerate the development of reinforcement learning algorithms for real-world applications. The benchmark project page is available at https://github.com/polixir/NeoRL2.

To survive in dynamic and uncertain environments, individuals must develop effective decision strategies that balance information gathering and decision commitment. Models of such strategies often prioritize either optimizing tangible payoffs, like reward rate, or gathering information to support a diversity of (possibly unknown) objectives. However, our understanding of the relative merits of these two approaches remains incomplete, in part because direct comparisons have been limited to idealized, static environments that lack the dynamic complexity of the real world. Here we compared the performance of normative reward- and information-seeking strategies in a dynamic foraging task. Both strategies show similar transitions between exploratory and exploitative behaviors as environmental uncertainty changes. However, we find subtle disparities in the actions they take, resulting in meaningful performance differences: whereas reward-seeking strategies generate slightly more reward on average, information-seeking strategies provide more consistent and predictable outcomes. Our findings support the adaptive value of information-seeking behaviors that can mitigate risk with minimal reward loss.

Without using explicit reward, direct preference optimization (DPO) employs paired human preference data to fine-tune generative models, a method that has garnered considerable attention in large language models (LLMs). However, exploration of aligning text-to-image (T2I) diffusion models with human preferences remains limited. In comparison to supervised fine-tuning, existing methods that align diffusion model suffer from low training efficiency and subpar generation quality due to the long Markov chain process and the intractability of the reverse process. To address these limitations, we introduce DDIM-InPO, an efficient method for direct preference alignment of diffusion models. Our approach conceptualizes diffusion model as a single-step generative model, allowing us to fine-tune the outputs of specific latent variables selectively. In order to accomplish this objective, we first assign implicit rewards to any latent variable directly via a reparameterization technique. Then we construct an Inversion technique to estimate appropriate latent variables for preference optimization. This modification process enables the diffusion model to only fine-tune the outputs of latent variables that have a strong correlation with the preference dataset. Experimental results indicate that our DDIM-InPO achieves state-of-the-art performance with just 400 steps of fine-tuning, surpassing all preference aligning baselines for T2I diffusion models in human preference evaluation tasks.

Reinforcement learning in non-stationary environments is challenging due to abrupt and unpredictable changes in dynamics, often causing traditional algorithms to fail to converge. However, in many real-world cases, non-stationarity has some structure that can be exploited to develop algorithms and facilitate theoretical analysis. We introduce one such structure, Switching Non-Stationary Markov Decision Processes (SNS-MDP), where environments switch over time-based on an underlying Markov chain. Under a fixed policy, the value function of an SNS-MDP admits a closed-form solution determined by the Markov chain's statistical properties, and despite the inherent non-stationarity, Temporal Difference (TD) learning methods still converge to the correct value function. Furthermore, policy improvement can be performed, and it is shown that policy iteration converges to the optimal policy. Moreover, since Q-learning converges to the optimal Q-function, it likewise yields the corresponding optimal policy. To illustrate the practical advantages of SNS-MDPs, we present an example in communication networks where channel noise follows a Markovian pattern, demonstrating how this framework can effectively guide decision-making in complex, time-varying contexts.

Saddle point optimization is a critical problem employed in numerous real-world applications, including portfolio optimization, generative adversarial networks, and robotics. It has been extensively studied in cases where the objective function is known and differentiable. Existing work in black-box settings with unknown objectives that can only be sampled either assumes convexity-concavity in the objective to simplify the problem or operates with noisy gradient estimators. In contrast, we introduce a framework inspired by Bayesian optimization which utilizes Gaussian processes to model the unknown (potentially nonconvex-nonconcave) objective and requires only zeroth-order samples. Our approach frames the saddle point optimization problem as a two-level process which can flexibly integrate existing and novel approaches to this problem. The upper level of our framework produces a model of the objective function by sampling in promising locations, and the lower level of our framework uses the existing model to frame and solve a general-sum game to identify locations to sample. This lower level procedure can be designed in complementary ways, and we demonstrate the flexibility of our approach by introducing variants which appropriately trade off between factors like runtime, the cost of function evaluations, and the number of available initial samples. We experimentally demonstrate these algorithms on synthetic and realistic datasets in black-box nonconvex-nonconcave settings, showcasing their ability to efficiently locate local saddle points in these contexts.

The study proposes an advanced machine learning approach to predict spine surgery outcomes by incorporating oversampling techniques and grid search optimization. A variety of models including GaussianNB, ComplementNB, KNN, Decision Tree, and optimized versions with RandomOverSampler and SMOTE were tested on a dataset of 244 patients, which included pre-surgical, psychometric, socioeconomic, and analytical variables. The enhanced KNN models achieved up to 76% accuracy and a 67% F1-score, while grid-search optimization further improved performance. The findings underscore the potential of these advanced techniques to aid healthcare professionals in decision-making, with future research needed to refine these models on larger and more diverse datasets.

This work addresses the challenge of enabling a team of quadrupedal robots to collaboratively tow a cable-connected load through cluttered and unstructured environments while avoiding obstacles. Leveraging cables allows the multi-robot system to navigate narrow spaces by maintaining slack when necessary. However, this introduces hybrid physical interactions due to alternating taut and slack states, with computational complexity that scales exponentially as the number of agents increases. To tackle these challenges, we developed a scalable and decentralized system capable of dynamically coordinating a variable number of quadrupedal robots while managing the hybrid physical interactions inherent in the load-towing task. At the core of this system is a novel multi-agent reinforcement learning (MARL)-based planner, designed for decentralized coordination. The MARL-based planner is trained using a centralized training with decentralized execution (CTDE) framework, enabling each robot to make decisions autonomously using only local (ego) observations. To accelerate learning and ensure effective collaboration across varying team sizes, we introduce a tailored training curriculum for MARL. Experimental results highlight the flexibility and scalability of the framework, demonstrating successful deployment with one to four robots in real-world scenarios and up to twelve robots in simulation. The decentralized planner maintains consistent inference times, regardless of the team size. Additionally, the proposed system demonstrates robustness to environment perturbations and adaptability to varying load weights. This work represents a step forward in achieving flexible and efficient multi-legged robotic collaboration in complex and real-world environments.

We introduce a domain-specific reward mechanism that maximizes yield recovery while minimizing chemical usage by effectively handling noisy infection data and enforcing physical field constraints via action masking. We conduct a rigorous empirical evaluation across diverse, realistic biotic stress scenarios, capturing varying infection distributions and severity levels in row-crop fields. The proposed scheme is evaluated thoroughly, showing the framework's effectiveness and robustness. Experimental results demonstrate that our approach significantly reduces non-target spraying, chemical consumption, and operational costs compared to baseline methods. Optimizing Navigation And Chemical Application in Precision Agriculture With Deep Reinforcement Learning And Conditional Action Tree Mahsa Khosravi a, Zhanhong Jiang b, Joshua R Waite b, Sarah Jones c, Hernan Torres c, Arti Singh c, Baskar Ganapathysubramanian b, Asheesh Kumar Singh c, Soumik Sarkar b a Department of Industrial and Manufacturing Systems Engineering, Iowa State University, Ames, Iowa, USA b Department of Mechanical Engineering, Iowa State University, Ames, Iowa, USA c Department of Agronomy, Iowa State University, Ames, Iowa, USAAbstract This paper presents a novel reinforcement learning (RL)-based planning scheme for optimized robotic management of biotic stresses in precision agriculture.