Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation

• URL: http://arxiv.org/abs/2305.10907v1
• Date: Thu, 18 May 2023 12:10:06 GMT
• Title: Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation
• Authors: Xinze Li, Yixin Cao, Muhao Chen, Aixin Sun
• Abstract summary: Goal-oriented Script Generation is a new task of generating a list of steps that can fulfill the given goal. In this paper, we propose to extend the task from the perspective of cognitive theory.
• Score: 41.79944184861954
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Goal-oriented Script Generation is a new task of generating a list of steps that can fulfill the given goal. In this paper, we propose to extend the task from the perspective of cognitive theory. Instead of a simple flat structure, the steps are typically organized hierarchically - Human often decompose a complex task into subgoals, where each subgoal can be further decomposed into steps. To establish the benchmark, we contribute a new dataset, propose several baseline methods, and set up evaluation metrics. Both automatic and human evaluation verify the high-quality of dataset, as well as the effectiveness of incorporating subgoals into hierarchical script generation. Furthermore, We also design and evaluate the model to discover subgoal, and find that it is a bit more difficult to decompose the goals than summarizing from segmented steps.

Related papers

• Learning Rational Subgoals from Demonstrations and Instructions [71.86713748450363]
  We present a framework for learning useful subgoals that support efficient long-term planning to achieve novel goals. At the core of our framework is a collection of rational subgoals (RSGs), which are essentially binary classifiers over the environmental states. Given a goal description, the learned subgoals and the derived dependencies facilitate off-the-shelf planning algorithms, such as A* and RRT.
  arXiv  Detail & Related papers  (2023-03-09T18:39:22Z)
• Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space [76.46113138484947]
  General-purpose robots require diverse repertoires of behaviors to complete challenging tasks in real-world unstructured environments. To address this issue, goal-conditioned reinforcement learning aims to acquire policies that can reach goals for a wide range of tasks on command. We propose Planning to Practice, a method that makes it practical to train goal-conditioned policies for long-horizon tasks.
  arXiv  Detail & Related papers  (2022-05-17T06:58:17Z)
• Autoregressive Search Engines: Generating Substrings as Document Identifiers [53.0729058170278]
  Autoregressive language models are emerging as the de-facto standard for generating answers. Previous work has explored ways to partition the search space into hierarchical structures. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
  arXiv  Detail & Related papers  (2022-04-22T10:45:01Z)
• Document-Level Text Simplification: Dataset, Criteria and Baseline [75.58761130635824]
  We define and investigate a new task of document-level text simplification. Based on Wikipedia dumps, we first construct a large-scale dataset named D-Wikipedia. We propose a new automatic evaluation metric called D-SARI that is more suitable for the document-level simplification task.
  arXiv  Detail & Related papers  (2021-10-11T08:15:31Z)
• Hierarchical Policy for Non-prehensile Multi-object Rearrangement with Deep Reinforcement Learning and Monte Carlo Tree Search [30.31462739429364]
  We propose a hierarchical policy to divide and conquer for non-prehensile multi-object rearrangement. In the high-level policy, the Monte Carlo Tree Search efficiently searches for the optimal rearrangement sequence among multiple objects. In the low-level policy, the robot plans the paths according to the order of path primitives and manipulates the objects to approach the goal poses one by one.
  arXiv  Detail & Related papers  (2021-09-18T17:24:37Z)
• Subgoal Search For Complex Reasoning Tasks [15.152111664776259]
  kSubS is a learned subgoal generator that produces a diversity of subgoals that are both achievable and closer to the solution. We show that a simple approach of generating $k$-th step ahead subgoals is surprisingly efficient on three challenging domains.
  arXiv  Detail & Related papers  (2021-08-25T12:40:04Z)
• Leveraging Class Hierarchies with Metric-Guided Prototype Learning [5.070542698701158]
  In many classification tasks, the set of target classes can be organized into a hierarchy. This structure induces a semantic distance between classes, and can be summarised under the form of a cost matrix. We propose to model the hierarchical class structure by integrating this metric in the supervision of a prototypical network.
  arXiv  Detail & Related papers  (2020-07-06T20:22:08Z)
• Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning [78.65083326918351]
  We consider alternatives to an implicit sequential planning assumption. We propose Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS) for approximating the optimal plan. We show that this algorithmic flexibility over planning order leads to improved results in navigation tasks in grid-worlds.
  arXiv  Detail & Related papers  (2020-04-23T18:08:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.