Search for: All records

Reinforcement Learning from Human Feedback (RLHF) has achieved impressive empirical successes while relying on a small amount of human feedback. However, there is limited theoretical justification for this phenomenon. Additionally, most recent studies focus on value-based algorithms despite the recent empirical successes of policy-based algorithms. In this work, we consider an RLHF algorithm based on policy optimization (PO-RLHF). The algorithm is based on the popular Policy Cover-Policy Gradient (PC-PG) algorithm, which assumes knowledge of the reward function. In PO-RLHF, knowledge of the reward function is not assumed and the algorithm relies on trajectory-based comparison feedback to infer the reward function. We provide performance bounds for PO-RLHF with low query complexity, which provides insight into why a small amount of human feedback may be sufficient to get good performance with RLHF. A key novelty is our trajectory-level elliptical potential analysis technique used to infer reward function parameters when comparison queries rather than reward observations are used. We provide and analyze algorithms in two settings: linear and neural function approximation, PG-RLHF and NN-PG-RLHF, respectively. 

Cascading bandits have gained popularity in recent years due to their applicability to recommendation systems and online advertising. In the cascading bandit model, at each timestep, an agent recommends an ordered subset of items (called an item list) from a pool of items, each associated with an unknown attraction probability. Then, the user examines the list, and clicks the first attractive item (if any), and after that, the agent receives a reward. The goal of the agent is to maximize the expected cumulative reward. However, the prior literature on cascading bandits ignores the influences of user states (e.g., historical behaviors) on recommendations and the change of states as the session proceeds. Motivated by this fact, we propose a generalized cascading RL framework, which considers the impact of user states and state transition into decisions. In cascading RL, we need to select items not only with large attraction probabilities but also leading to good successor states. This imposes a huge computational challenge due to the combinatorial action space. To tackle this challenge, we delve into the properties of value functions, and design an oracle BestPerm to efficiently find the optimal item list. Equipped with BestPerm, we develop two algorithms CascadingVI and CascadingBPI, which are both computation-efficient and sample-efficient, and provide near-optimal regret and sample complexity guarantees. Furthermore, we present experiments to show the improved computational and sample efficiencies of our algorithms compared to straightforward adaptations of existing RL algorithms in practice. 

Self-supervised training methods for transformers have demonstrated remarkable performance across various domains. Previous transformer-based models, such as masked autoencoders (MAE), typically utilize a single normalization layer for both the class token [CLS] and the tokens. We propose in this paper a new yet simple normalization method that separately normalizes embedding vectors respectively corresponding to normal tokens and the [CLS] token, in order to better capture their distinct characteristics and enhance downstream task performance. Our empirical study shows that the [CLS] embeddings learned with our separate normalization layer better encode the global contextual information and are distributed more uniformly in its anisotropic space. When the conventional normalization layer is replaced with a separate normalization layer, we observe an average 2.7% performance improvement in learning tasks from the image, natural language, and graph domains. 

Molecular Representation Learning (MRL) has proven impactful in numerous biochemical applications such as drug discovery and enzyme design. While Graph Neural Networks (GNNs) are effective at learning molecular representations from a 2D molecular graph or a single 3D structure, existing works often overlook the flexible nature of molecules, which continuously interconvert across conformations via chemical bond rotations and minor vibrational perturbations. To better account for molecular flexibility, some recent works formulate MRL as an ensemble learning problem, focusing on explicitly learning from a set of conformer structures. However, most of these studies have limited datasets, tasks, and models. In this work, we introduce the first MoleculAR Conformer Ensemble Learning (MARCEL) benchmark to thoroughly evaluate the potential of learning on con- former ensembles and suggest promising research directions. MARCEL includes four datasets covering diverse molecule- and reaction-level properties of chemically diverse molecules including organocatalysts and transition-metal catalysts, extending beyond the scope of common GNN benchmarks that are confined to drug-like molecules. In addition, we conduct a comprehensive empirical study, which benchmarks representative 1D, 2D, and 3D MRL models, along with two strategies that explicitly incorporate conformer ensembles into 3D models. Our findings reveal that direct learning from an accessible conformer space can improve performance on a variety of tasks and models. 

Precision agricultural robots require highresolution navigation solutions. In this paper, we introduce a robust neural-inertial sequence learning approach to track such robots with ultra-intermittent GNSS updates. First, we propose an ultra-lightweight neural-Kalman filter that can track agricultural robots within 1.4 m (1.4 - 5.8× better than competing techniques), while tracking within 2.75 m with 20 mins of GPS outage. Second, we introduce a user-friendly video-processing toolbox to generate high-resolution (±5 cm) position data for fine-tuning pre-trained neural-inertial models in the field. Third, we introduce the first and largest (6.5 hours, 4.5 km, 3 phases) public neural-inertial navigation dataset for precision agricultural robots. The dataset, toolbox, and code are available at: https://github.com/nesl/agrobot. 

Systems consisting of interacting agents are prevalent in the world, ranging from dynamical systems in physics to complex biological networks. To build systems which can interact robustly in the real world, it is thus important to be able to infer the precise interactions governing such systems. Existing approaches typically dis- cover such interactions by explicitly modeling the feed-forward dynamics of the trajectories. In this work, we propose Neural Interaction Inference with Potentials (NIIP) as an alternative approach to discover such interactions that enables greater flexibility in trajectory modeling: it discovers a set of relational potentials, represented as energy functions, which when minimized reconstruct the original trajectory. NIIP assigns low energy to the subset of trajectories which respect the relational constraints observed. We illustrate that with these representations NIIP displays unique capabilities in test-time. First, it allows trajectory manipulation, such as interchanging interaction types across separately trained models, as well as trajectory forecasting. Additionally, it allows adding external hand-crafted potentials at test-time. Finally, NIIP enables the detection of out-of-distribution samples and anomalies without explicit training. 

Systems consisting of interacting agents are prevalent in the world, ranging from dynamical systems in physics to complex biological networks. To build systems which can interact robustly in the real world, it is thus important to be able to infer the precise interactions governing such systems. Existing approaches typically discover such interactions by explicitly modeling the feed-forward dynamics of the trajectories. In this work, we propose Neural Interaction Inference with Potentials (NIIP) as an alternative approach to discover such interactions that enables greater flexibility in trajectory modeling: it discovers a set of relational potentials, represented as energy functions, which when minimized reconstruct the original trajectory. NIIP assigns low energy to the subset of trajectories which respect the relational constraints observed. We illustrate that with these representations NIIP displays unique capabilities in test-time. First, it allows trajectory manipulation, such as interchanging interaction types across separately trained models, as well as trajectory forecasting. Additionally, it allows adding external hand-crafted potentials at test-time. Finally, NIIP enables the detection of out-of-distribution samples and anomalies without explicit training.