In recent years, model-free reinforcement learning (MFRL) has achieved tremendous success on a wide range of simulated domains, e .

Q1: ...the claim that the algorithm really manages to align the latent distributions of real and simulated data... We will revise the inappropriate statements in the final version. Q2: In the model adaptation phase, are state-action pairs simply sampled randomly from their respective buffers? Do you have results for a single, monolithic model? Q4: Did you investigate the reasons for the slow learning in the 500 steps on InvertedPendulum compared to PETS? Q1: The experiments shown in Figure 2 do not outperform MBPO beyond the confidence bounds.

Organizations are rapidly adopting Large Language Models (LLMs) to transform their operations, yet they lack clear guidance on key decisions for adoption and implementation. While LLMs offer powerful capabilities in content generation, assisted coding, and process automation, businesses face critical challenges in data security, LLM solution development approach, infrastructure requirements, and deployment strategies. Healthcare providers must protect patient data while leveraging LLMs for medical analysis, financial institutions need to balance automated customer service with regulatory compliance, and software companies seek to enhance development productivity while maintaining code security. This article presents a systematic six-step decision framework for LLM adoption, helping organizations navigate from initial application selection to final deployment. Based on extensive interviews and analysis of successful and failed implementations, our framework provides practical guidance for business leaders to align technological capabilities with business objectives. Through key decision points and real-world examples from both B2B and B2C contexts, organizations can make informed decisions about LLM adoption while ensuring secure and efficient integration across various use cases, from customer service automation to content creation and advanced analytics.

Presenting users with diverse responses from foundation models is crucial for enhancing user experience and accommodating varying preferences. However, generating multiple high-quality and diverse responses without sacrificing accuracy remains a challenge, especially when using greedy sampling. In this work, we propose a novel framework, Synthesize-Partition-Adapt (SP A), that leverages the abundant synthetic data available in many domains to elicit diverse responses from foundation models. By leveraging signal provided by data attribution methods such as influence function, SP A partitions data into subsets, each targeting unique aspects of the data, and trains multiple model adaptations optimized for these subsets. Experimental results demonstrate the effectiveness of our approach in diversifying foundation model responses while maintaining high quality, showcased through the HumanEval and MBPP tasks in the code generation domain and several tasks in the natural language understanding domain, highlighting its potential to enrich user experience across various applications.

This work discusses how to achieve worst-case Out-Of-Distribution (OOD) generalization for a variety of distributions based on a relatively small labeling cost. The problem has broad applications, especially in non-i.i.d.

Maximum likelihood (ML) is a concept to describe the theoretic insights of clustering algorithms. As it is not easy to optimize Eq.14 directly, we employ a surrogate function to lower-bound the Please note the notation " t m" shows that the k is encoded by a historical encoder. In practice, we achieve Eq. 9 by minimizing a historical contrastive instance discrimination loss: Please note that Eq. 10 is an instance of Eq. 9. The two equations look different due to: 1) Eq. 10 Proposition 2 The HCID is convergent under certain conditions. We have illustrated in Section A.1 that the inequality in Eq.11 holds with equality if One possible way to achieve Eq. 13 is to conduct gradient descent by minimizing the historical Different from the classical expectation maximization (mentioned in Section A.1) that consists It can be observed that Eq. 16 is the same as Eq. 15 except involving an extra weighting element In the following, we show the optimization of Eq. 16 is a CEM process.

Besides Wasserstein distance, we can use other distribution divergence metrics to align the features. MMD is another instance of IPM when the witness function class is the unit ball in a reproducing kernel Hilbert space (RKHS). The results on three environments are shown in Figure 5. We show the one-step model losses during the experiments in the other four environments in Figure D.5. We find that the conclusion in Section 5.2 still holds in these four environments.

Planetary exploration missions require robots capable of navigating extreme and unknown environments. While wheeled rovers have dominated past missions, their mobility is limited to traversable surfaces. Legged robots, especially quadrupeds, can overcome these limitations by handling uneven, obstacle-rich, and deformable terrains. However, deploying such robots in unknown conditions is challenging due to the need for environment-specific control, which is infeasible when terrain and robot parameters are uncertain. This work presents a modular control framework that combines model-based dynamic control with online model adaptation and adaptive footstep planning to address uncertainties in both robot and terrain properties. The framework includes state estimation for quadrupeds with and without contact sensing, supports runtime reconfiguration, and is integrated into ROS 2 with open-source availability. Its performance was validated on two quadruped platforms, multiple hardware architectures, and in a volcano field test, where the robot walked over 700 m.