Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, honest, and harmless) assistant. Alignment with humans assumes paramount significance, and reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. Current technical routes usually include \textbf{reward models} to measure human preferences, \textbf{Proximal Policy Optimization} (PPO) to optimize policy model outputs, and \textbf{process supervision} to improve step-by-step reasoning capabilities. However, due to the challenges of reward design, environment interaction, and agent training, coupled with huge trial and error cost of large language models, there is a significant barrier for AI researchers to motivate the development of technical alignment and safe landing of LLMs. The stable training of RLHF has still been a puzzle. In the first report, we dissect the framework of RLHF, re-evaluate the inner workings of PPO, and explore how the parts comprising PPO algorithms impact policy agent training. We identify policy constraints being the key factor for the effective implementation of the PPO algorithm. Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model. Based on our main results, we perform a comprehensive analysis of RLHF abilities compared with SFT models and ChatGPT. The absence of open-source implementations has posed significant challenges to the investigation of LLMs alignment. Therefore, we are eager to release technical reports, reward models and PPO codes, aiming to make modest contributions to the advancement of LLMs.

We consider the problem of sampling transition paths between two given metastable states of a molecular system, e.g. a folded and unfolded protein or products and reactants of a chemical reaction. Due to the existence of high energy barriers separating the states, these transition paths are unlikely to be sampled with standard Molecular Dynamics (MD) simulation. Traditional methods to augment MD with a bias potential to increase the probability of the transition rely on a dimensionality reduction step based on Collective Variables (CVs). Unfortunately, selecting appropriate CVs requires chemical intuition and traditional methods are therefore not always applicable to larger systems. Additionally, when incorrect CVs are used, the bias potential might not be minimal and bias the system along dimensions irrelevant to the transition. Showing a formal relation between the problem of sampling molecular transition paths, the Schr\"odinger bridge problem and stochastic optimal control with neural network policies, we propose a machine learning method for sampling said transitions. Unlike previous non-machine learning approaches our method, named PIPS, does not depend on CVs. We show that our method successful generates low energy transitions for Alanine Dipeptide as well as the larger Polyproline and Chignolin proteins.

This work is dedicated to the study of how uncertainty estimation of the human motion prediction can be embedded into constrained optimization techniques, such as Model Predictive Control (MPC) for the social robot navigation. We propose several cost objectives and constraint functions obtained from the uncertainty of predicting pedestrian positions and related to the probability of the collision that can be applied to the MPC, and all the different variants are compared in challenging scenes with multiple agents. The main question this paper tries to answer is: what are the most important uncertainty-based criteria for social MPC? For that, we evaluate the proposed approaches with several social navigation metrics in an extensive set of scenarios of different complexity in reproducible synthetic environments. The main outcome of our study is a foundation for a practical guide on when and how to use uncertainty-aware approaches for social robot navigation in practice and what are the most effective criteria.

In robotic tasks, changes in reference frames typically do not influence the underlying physical properties of the system, which has been known as invariance of physical laws. These changes, which preserve distance, encompass isometric transformations such as translations, rotations, and reflections, collectively known as the Euclidean group. In this work, we delve into the design of improved learning algorithms for reinforcement learning and planning tasks that possess Euclidean group symmetry. We put forth a theory on that unify prior work on discrete and continuous symmetry in reinforcement learning, planning, and optimal control. Algorithm side, we further extend the 2D path planning with value-based planning to continuous MDPs and propose a pipeline for constructing equivariant sampling-based planning algorithms. Our work is substantiated with empirical evidence and illustrated through examples that explain the benefits of equivariance to Euclidean symmetry in tackling natural control problems.

This paper presents RAYEN, a framework to impose hard convex constraints on the output or latent variable of a neural network. RAYEN guarantees that, for any input or any weights of the network, the constraints are satisfied at all times. Compared to other approaches, RAYEN does not perform a computationally-expensive orthogonal projection step onto the feasible set, does not rely on soft constraints (which do not guarantee the satisfaction of the constraints at test time), does not use conservative approximations of the feasible set, and does not perform a potentially slow inner gradient descent correction to enforce the constraints. RAYEN supports any combination of linear, convex quadratic, second-order cone (SOC), and linear matrix inequality (LMI) constraints, achieving a very small computational overhead compared to unconstrained networks. For example, it is able to impose 1K quadratic constraints on a 1K-dimensional variable with an overhead of less than 8 ms, and an LMI constraint with 300x300 dense matrices on a 10K-dimensional variable in less than 12 ms. When used in neural networks that approximate the solution of constrained optimization problems, RAYEN achieves computation times between 20 and 7468 times faster than state-of-the-art algorithms, while guaranteeing the satisfaction of the constraints at all times and obtaining a cost very close to the optimal one.

For underwater vehicles, robotic applications have the added difficulty of operating in highly unstructured and dynamic environments. Environmental effects impact not only the dynamics and controls of the robot but also the perception and sensing modalities. Acoustic sensors, which inherently use mechanically vibrated signals for measuring range or velocity, are particularly prone to the effects that such dynamic environments induce. This paper presents an uncertainty-aware localization and mapping framework that accounts for induced disturbances in acoustic sensing modalities for underwater robots operating near the surface in dynamic wave conditions. For the state estimation task, the uncertainty is accounted for as the added noise caused by the environmental disturbance. The mapping method uses an adaptive kernel-based method to propagate measurement and pose uncertainty into an occupancy map. Experiments are carried out in a wave tank environment to perform qualitative and quantitative evaluations of the proposed method. More details about this project can be found at https://umfieldrobotics.github.io/PUMA.github.io.

Forecasting how landslides will evolve over time or whether they will fail is a challenging task due to a variety of factors, both internal and external. Despite their considerable potential to address these challenges, deep learning techniques lack interpretability, undermining the credibility of the forecasts they produce. The recent development of transformer-based deep learning offers untapped possibilities for forecasting landslides with unprecedented interpretability and nonlinear feature learning capabilities. Here, we present a deep learning pipeline that is capable of predicting landslide behavior holistically, which employs a transformer-based network called LFIT to learn complex nonlinear relationships from prior knowledge and multiple source data, identifying the most relevant variables, and demonstrating a comprehensive understanding of landslide evolution and temporal patterns. By integrating prior knowledge, we provide improvement in holistic landslide forecasting, enabling us to capture diverse responses to various influencing factors in different local landslide areas. Using deformation observations as proxies for measuring the kinetics of landslides, we validate our approach by training models to forecast reservoir landslides in the Three Gorges Reservoir and creeping landslides on the Tibetan Plateau. When prior knowledge is incorporated, we show that interpretable landslide forecasting effectively identifies influential factors across various landslides. It further elucidates how local areas respond to these factors, making landslide behavior and trends more interpretable and predictable. The findings from this study will contribute to understanding landslide behavior in a new way and make the proposed approach applicable to other complex disasters influenced by internal and external factors in the future.

Predicting emissions for gas turbines is critical for monitoring harmful pollutants being released into the atmosphere. In this study, we evaluate the performance of machine learning models for predicting emissions for gas turbines. We compare an existing predictive emissions model, a first principles-based Chemical Kinetics model, against two machine learning models we developed based on SAINT and XGBoost, to demonstrate improved predictive performance of nitrogen oxides (NOx) and carbon monoxide (CO) using machine learning techniques. Our analysis utilises a Siemens Energy gas turbine test bed tabular dataset to train and validate the machine learning models. Additionally, we explore the trade-off between incorporating more features to enhance the model complexity, and the resulting presence of increased missing values in the dataset.

Optimizing quantum circuits is challenging due to the very large search space of functionally equivalent circuits and the necessity of applying transformations that temporarily decrease performance to achieve a final performance improvement. This paper presents Quarl, a learning-based quantum circuit optimizer. Applying reinforcement learning (RL) to quantum circuit optimization raises two main challenges: the large and varying action space and the non-uniform state representation. Quarl addresses these issues with a novel neural architecture and RL-training procedure. Our neural architecture decomposes the action space into two parts and leverages graph neural networks in its state representation, both of which are guided by the intuition that optimization decisions can be mostly guided by local reasoning while allowing global circuit-wide reasoning. Our evaluation shows that Quarl significantly outperforms existing circuit optimizers on almost all benchmark circuits. Surprisingly, Quarl can learn to perform rotation merging, a complex, non-local circuit optimization implemented as a separate pass in existing optimizers.

The Electron-Ion Collider (EIC), a state-of-the-art facility for studying the strong force, is expected to begin commissioning its first experiments in 2028. This is an opportune time for artificial intelligence (AI) to be included from the start at this facility and in all phases that lead up to the experiments. The second annual workshop organized by the AI4EIC working group, which recently took place, centered on exploring all current and prospective application areas of AI for the EIC. This workshop is not only beneficial for the EIC, but also provides valuable insights for the newly established ePIC collaboration at EIC. This paper summarizes the different activities and R&D projects covered across the sessions of the workshop and provides an overview of the goals, approaches and strategies regarding AI/ML in the EIC community, as well as cutting-edge techniques currently studied in other experiments.