Spreadsheet manipulation is widely existing in most daily works and significantly improves working efficiency. Large language model (LLM) has been recently attempted for automatic spreadsheet manipulation but has not yet been investigated in complicated and realistic tasks where reasoning challenges exist (e.g., long horizon manipulation with multi-step reasoning and ambiguous requirements). To bridge the gap with the real-world requirements, we introduce $\textbf{SheetRM}$, a benchmark featuring long-horizon and multi-category tasks with reasoning-dependent manipulation caused by real-life challenges. To mitigate the above challenges, we further propose $\textbf{SheetAgent}$, a novel autonomous agent that utilizes the power of LLMs. SheetAgent consists of three collaborative modules: $\textit{Planner}$, $\textit{Informer}$, and $\textit{Retriever}$, achieving both advanced reasoning and accurate manipulation over spreadsheets without human interaction through iterative task reasoning and reflection. Extensive experiments demonstrate that SheetAgent delivers 20-30% pass rate improvements on multiple benchmarks over baselines, achieving enhanced precision in spreadsheet manipulation and demonstrating superior table reasoning abilities. More details and visualizations are available at https://sheetagent.github.io.
Recently, there has been considerable attention towards leveraging large language models (LLMs) to enhance decision-making processes. However, aligning the natural language text instructions generated by LLMs with the vectorized operations required for execution presents a significant challenge, often necessitating task-specific details. To circumvent the need for such task-specific granularity, inspired by preference-based policy learning approaches, we investigate the utilization of multimodal LLMs to provide automated preference feedback solely from image inputs to guide decision-making. In this study, we train a multimodal LLM, termed CriticGPT, capable of understanding trajectory videos in robot manipulation tasks, serving as a critic to offer analysis and preference feedback. Subsequently, we validate the effectiveness of preference labels generated by CriticGPT from a reward modeling perspective. Experimental evaluation of the algorithm's preference accuracy demonstrates its effective generalization ability to new tasks. Furthermore, performance on Meta-World tasks reveals that CriticGPT's reward model efficiently guides policy learning, surpassing rewards based on state-of-the-art pre-trained representation models.
Hierarchical reinforcement learning (HRL) provides a promising solution for complex tasks with sparse rewards of intelligent agents, which uses a hierarchical framework that divides tasks into subgoals and completes them sequentially. However, current methods struggle to find suitable subgoals for ensuring a stable learning process. Without additional guidance, it is impractical to rely solely on exploration or heuristics methods to determine subgoals in a large goal space. To address the issue, We propose a general hierarchical reinforcement learning framework incorporating human feedback and dynamic distance constraints (MENTOR). MENTOR acts as a "mentor", incorporating human feedback into high-level policy learning, to find better subgoals. As for low-level policy, MENTOR designs a dual policy for exploration-exploitation decoupling respectively to stabilize the training. Furthermore, although humans can simply break down tasks into subgoals to guide the right learning direction, subgoals that are too difficult or too easy can still hinder downstream learning efficiency. We propose the Dynamic Distance Constraint (DDC) mechanism dynamically adjusting the space of optional subgoals. Thus MENTOR can generate subgoals matching the low-level policy learning process from easy to hard. Extensive experiments demonstrate that MENTOR uses a small amount of human feedback to achieve significant improvement in complex tasks with sparse rewards.
Reinforcement Learning with Human Feedback (RLHF) has received significant attention for performing tasks without the need for costly manual reward design by aligning human preferences. It is crucial to consider diverse human feedback types and various learning methods in different environments. However, quantifying progress in RLHF with diverse feedback is challenging due to the lack of standardized annotation platforms and widely used unified benchmarks. To bridge this gap, we introduce Uni-RLHF, a comprehensive system implementation tailored for RLHF. It aims to provide a complete workflow from real human feedback, fostering progress in the development of practical problems. Uni-RLHF contains three packages: 1) a universal multi-feedback annotation platform, 2) large-scale crowdsourced feedback datasets, and 3) modular offline RLHF baseline implementations. Uni-RLHF develops a user-friendly annotation interface tailored to various feedback types, compatible with a wide range of mainstream RL environments. We then establish a systematic pipeline of crowdsourced annotations, resulting in large-scale annotated datasets comprising more than 15 million steps across 30+ popular tasks. Through extensive experiments, the results in the collected datasets demonstrate competitive performance compared to those from well-designed manual rewards. We evaluate various design choices and offer insights into their strengths and potential areas of improvement. We wish to build valuable open-source platforms, datasets, and baselines to facilitate the development of more robust and reliable RLHF solutions based on realistic human feedback. The website is available at https://uni-rlhf.github.io/.
Diffusion planning has been recognized as an effective decision-making paradigm in various domains. The capability of conditionally generating high-quality long-horizon trajectories makes it a promising research direction. However, existing diffusion planning methods suffer from low decision-making frequencies due to the expensive iterative sampling cost. To address this issue, we introduce DiffuserLite, a super fast and lightweight diffusion planning framework. DiffuserLite employs a planning refinement process (PRP) to generate coarse-to-fine-grained trajectories, significantly reducing the modeling of redundant information and leading to notable increases in decision-making frequency. Our experimental results demonstrate that DiffuserLite achieves a decision-making frequency of $122$Hz ($112.7$x faster than previous mainstream frameworks) and reaches state-of-the-art performance on D4RL benchmarks. In addition, our neat DiffuserLite framework can serve as a flexible plugin to enhance decision frequency in other diffusion planning algorithms, providing a structural design reference for future works. More details and visualizations are available at https://diffuserlite.github.io/.
Aligning agent behaviors with diverse human preferences remains a challenging problem in reinforcement learning (RL), owing to the inherent abstractness and mutability of human preferences. To address these issues, we propose AlignDiff, a novel framework that leverages RL from Human Feedback (RLHF) to quantify human preferences, covering abstractness, and utilizes them to guide diffusion planning for zero-shot behavior customizing, covering mutability. AlignDiff can accurately match user-customized behaviors and efficiently switch from one to another. To build the framework, we first establish the multi-perspective human feedback datasets, which contain comparisons for the attributes of diverse behaviors, and then train an attribute strength model to predict quantified relative strengths. After relabeling behavioral datasets with relative strengths, we proceed to train an attribute-conditioned diffusion model, which serves as a planner with the attribute strength model as a director for preference aligning at the inference phase. We evaluate AlignDiff on various locomotion tasks and demonstrate its superior performance on preference matching, switching, and covering compared to other baselines. Its capability of completing unseen downstream tasks under human instructions also showcases the promising potential for human-AI collaboration. More visualization videos are released on https://aligndiff.github.io/.
Recently, diffusion model shines as a promising backbone for the sequence modeling paradigm in offline reinforcement learning(RL). However, these works mostly lack the generalization ability across tasks with reward or dynamics change. To tackle this challenge, in this paper we propose a task-oriented conditioned diffusion planner for offline meta-RL(MetaDiffuser), which considers the generalization problem as conditional trajectory generation task with contextual representation. The key is to learn a context conditioned diffusion model which can generate task-oriented trajectories for planning across diverse tasks. To enhance the dynamics consistency of the generated trajectories while encouraging trajectories to achieve high returns, we further design a dual-guided module in the sampling process of the diffusion model. The proposed framework enjoys the robustness to the quality of collected warm-start data from the testing task and the flexibility to incorporate with different task representation method. The experiment results on MuJoCo benchmarks show that MetaDiffuser outperforms other strong offline meta-RL baselines, demonstrating the outstanding conditional generation ability of diffusion architecture.
Training labels for graph embedding algorithms could be costly to obtain in many practical scenarios. Active learning (AL) algorithms are very helpful to obtain the most useful labels for training while keeping the total number of label queries under a certain budget. The existing Active Graph Embedding framework proposes to use centrality score, density score, and entropy score to evaluate the value of unlabeled nodes, and it has been shown to be capable of bringing some improvement to the node classification tasks of Graph Convolutional Networks. However, when evaluating the importance of unlabeled nodes, it fails to consider the influence of existing labeled nodes on the value of unlabeled nodes. In other words, given the same unlabeled node, the computed informative score is always the same and is agnostic to the labeled node set. With the aim to address this limitation, in this work, we introduce 3 dissimilarity-based information scores for active learning: feature dissimilarity score (FDS), structure dissimilarity score (SDS), and embedding dissimilarity score (EDS). We find out that those three scores are able to take the influence of the labeled set on the value of unlabeled candidates into consideration, boosting our AL performance. According to experiments, our newly proposed scores boost the classification accuracy by 2.1% on average and are capable of generalizing to different Graph Neural Network architectures.
Unsupervised reinforcement learning (URL) poses a promising paradigm to learn useful behaviors in a task-agnostic environment without the guidance of extrinsic rewards to facilitate the fast adaptation of various downstream tasks. Previous works focused on the pre-training in a model-free manner while lacking the study of transition dynamics modeling that leaves a large space for the improvement of sample efficiency in downstream tasks. To this end, we propose an Efficient Unsupervised Reinforcement Learning Framework with Multi-choice Dynamics model (EUCLID), which introduces a novel model-fused paradigm to jointly pre-train the dynamics model and unsupervised exploration policy in the pre-training phase, thus better leveraging the environmental samples and improving the downstream task sampling efficiency. However, constructing a generalizable model which captures the local dynamics under different behaviors remains a challenging problem. We introduce the multi-choice dynamics model that covers different local dynamics under different behaviors concurrently, which uses different heads to learn the state transition under different behaviors during unsupervised pre-training and selects the most appropriate head for prediction in the downstream task. Experimental results in the manipulation and locomotion domains demonstrate that EUCLID achieves state-of-the-art performance with high sample efficiency, basically solving the state-based URLB benchmark and reaching a mean normalized score of 104.0$\pm$1.2$\%$ in downstream tasks with 100k fine-tuning steps, which is equivalent to DDPG's performance at 2M interactive steps with 20x more data.