Skill-based reinforcement learning (RL) approaches have shown considerable promise, especially in solving long-horizon tasks via hierarchical structures. These skills, learned task-agnostically from offline datasets, can accelerate the policy learning process for new tasks. Yet, the application of these skills in different domains remains restricted due to their inherent dependency on the datasets, which poses a challenge when attempting to learn a skill-based policy via RL for a target domain different from the datasets' domains. In this paper, we present a novel offline skill learning framework DuSkill which employs a guided Diffusion model to generate versatile skills extended from the limited skills in datasets, thereby enhancing the robustness of policy learning for tasks in different domains. Specifically, we devise a guided diffusion-based skill decoder in conjunction with the hierarchical encoding to disentangle the skill embedding space into two distinct representations, one for encapsulating domain-invariant behaviors and the other for delineating the factors that induce domain variations in the behaviors. Our DuSkill framework enhances the diversity of skills learned offline, thus enabling to accelerate the learning procedure of high-level policies for different domains. Through experiments, we show that DuSkill outperforms other skill-based imitation learning and RL algorithms for several long-horizon tasks, demonstrating its benefits in few-shot imitation and online RL.
One-shot imitation is to learn a new task from a single demonstration, yet it is a challenging problem to adopt it for complex tasks with the high domain diversity inherent in a non-stationary environment. To tackle the problem, we explore the compositionality of complex tasks, and present a novel skill-based imitation learning framework enabling one-shot imitation and zero-shot adaptation; from a single demonstration for a complex unseen task, a semantic skill sequence is inferred and then each skill in the sequence is converted into an action sequence optimized for environmental hidden dynamics that can vary over time. Specifically, we leverage a vision-language model to learn a semantic skill set from offline video datasets, where each skill is represented on the vision-language embedding space, and adapt meta-learning with dynamics inference to enable zero-shot skill adaptation. We evaluate our framework with various one-shot imitation scenarios for extended multi-stage Meta-world tasks, showing its superiority in learning complex tasks, generalizing to dynamics changes, and extending to different demonstration conditions and modalities, compared to other baselines.
This work explores the zero-shot adaptation capability of semantic skills, semantically interpretable experts' behavior patterns, in cross-domain settings, where a user input in interleaved multi-modal snippets can prompt a new long-horizon task for different domains. In these cross-domain settings, we present a semantic skill translator framework SemTra which utilizes a set of multi-modal models to extract skills from the snippets, and leverages the reasoning capabilities of a pretrained language model to adapt these extracted skills to the target domain. The framework employs a two-level hierarchy for adaptation: task adaptation and skill adaptation. During task adaptation, seq-to-seq translation by the language model transforms the extracted skills into a semantic skill sequence, which is tailored to fit the cross-domain contexts. Skill adaptation focuses on optimizing each semantic skill for the target domain context, through parametric instantiations that are facilitated by language prompting and contrastive learning-based context inferences. This hierarchical adaptation empowers the framework to not only infer a complex task specification in one-shot from the interleaved multi-modal snippets, but also adapt it to new domains with zero-shot learning abilities. We evaluate our framework with Meta-World, Franka Kitchen, RLBench, and CARLA environments. The results clarify the framework's superiority in performing long-horizon tasks and adapting to different domains, showing its broad applicability in practical use cases, such as cognitive robots interpreting abstract instructions and autonomous vehicles operating under varied configurations.
Recently, deep reinforcement learning (RL) has proven its feasibility in solving combinatorial optimization problems (COPs). The learning-to-rank techniques have been studied in the field of information retrieval. While several COPs can be formulated as the prioritization of input items, as is common in the information retrieval, it has not been fully explored how the learning-to-rank techniques can be incorporated into deep RL for COPs. In this paper, we present the learning-to-rank distillation-based COP framework, where a high-performance ranking policy obtained by RL for a COP can be distilled into a non-iterative, simple model, thereby achieving a low-latency COP solver. Specifically, we employ the approximated ranking distillation to render a score-based ranking model learnable via gradient descent. Furthermore, we use the efficient sequence sampling to improve the inference performance with a limited delay. With the framework, we demonstrate that a distilled model not only achieves comparable performance to its respective, high-performance RL, but also provides several times faster inferences. We evaluate the framework with several COPs such as priority-based task scheduling and multidimensional knapsack, demonstrating the benefits of the framework in terms of inference latency and performance.
Deep Learning has been recently recognized as one of the feasible solutions to effectively address combinatorial optimization problems, which are often considered important yet challenging in various research domains. In this work, we first present how to adopt Deep Learning for real-time task scheduling through our preliminary work upon fixed priority global scheduling (FPGS) problems. We then briefly discuss possible generalizations of Deep Learning adoption for several realistic and complicated FPGS scenarios, e.g., scheduling tasks with dependency, mixed-criticality task scheduling. We believe that there are many opportunities for leveraging advanced Deep Learning technologies to improve the quality of scheduling in various system configurations and problem scenarios.
A recommender system generates personalized recommendations for a user by computing the preference score of items, sorting the items according to the score, and filtering the top-Kitemswith high scores. While sorting and ranking items are integral for this recommendation procedure,it is nontrivial to incorporate them in the process of end-to-end model training since sorting is non-differentiable and hard to optimize with gradient-based updates. This incurs the inconsistency issue between the existing learning objectives and ranking-based evaluation metrics of recommendation models. In this work, we present DRM (differentiable ranking metric) that mitigates the inconsistency and improves recommendation performance, by employing the differentiable relaxation of ranking-based evaluation metrics. Via experiments with several real-world datasets, we demonstrate that the joint learning of the DRM cost function upon existing factor based recommendation models significantly improves the quality of recommendations, in comparison with other state-of-the-art recommendation methods.
A recommender system recommends a few items for a user by sorting items according to their predicted preferences and filter items with the highest predicted preferences. While sorting and selecting top-K items are an inherent part of the personalized recommendation, it is nontrivial to incorporate them in the process of end-to-end model training since sorting is not differentiable and impossible to optimize with gradient based updates. Instead, existing recommenders optimize surrogate objectives, often rendering suboptimal quality of recommendations. In this paper, we propose the differentiable ranking metrics (DRM), a differentiable relaxation of evaluation metrics such as Precision and Recall. DRM maximizes the evaluation metrics for recommendation models directly. Via experiments with several real-world datasets, we demonstrate that the joint learning of the DRM cost function upon existing factor-based recommendation models improves the quality of recommendations significantly, in comparison with other state-of-the-art recommendation methods.