Hierarchical Meta-Reinforcement Learning via Automated Macro-Action Discovery

• URL: http://arxiv.org/abs/2412.11930v1
• Date: Mon, 16 Dec 2024 16:15:36 GMT
• Title: Hierarchical Meta-Reinforcement Learning via Automated Macro-Action Discovery
• Authors: Minjae Cho, Chuangchuang Sun,
• Abstract summary: It is still challenging to learn performant policies across multiple complex and high-dimensional tasks. We propose a novel architecture with three hierarchical levels for 1) learning task representations, 2) discovering task-agnostic macro-actions in an automated manner, and 3) learning primitive actions.
• Score: 4.0847743592744905
• License:
• Abstract: Meta-Reinforcement Learning (Meta-RL) enables fast adaptation to new testing tasks. Despite recent advancements, it is still challenging to learn performant policies across multiple complex and high-dimensional tasks. To address this, we propose a novel architecture with three hierarchical levels for 1) learning task representations, 2) discovering task-agnostic macro-actions in an automated manner, and 3) learning primitive actions. The macro-action can guide the low-level primitive policy learning to more efficiently transition to goal states. This can address the issue that the policy may forget previously learned behavior while learning new, conflicting tasks. Moreover, the task-agnostic nature of the macro-actions is enabled by removing task-specific components from the state space. Hence, this makes them amenable to re-composition across different tasks and leads to promising fast adaptation to new tasks. Also, the prospective instability from the tri-level hierarchies is effectively mitigated by our innovative, independently tailored training schemes. Experiments in the MetaWorld framework demonstrate the improved sample efficiency and success rate of our approach compared to previous state-of-the-art methods.

Related papers

• RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World [18.998643114600053]
  RoboMatrix is a skill-centric and hierarchical framework for scalable task planning and execution. We first introduce a novel skill-centric paradigm that extracts the common meta-skills from different complex tasks. To fully leverage meta-skills, we develop a hierarchical framework that decouples complex robot tasks into three interconnected layers.
  arXiv  Detail & Related papers  (2024-11-29T17:36:03Z)
• Meta-Learning with Heterogeneous Tasks [42.695853959923625]
  Heterogeneous Tasks Robust Meta-learning (HeTRoM) An efficient iterative optimization algorithm based on bi-level optimization. Results demonstrate that our method provides flexibility, enabling users to adapt to diverse task settings.
  arXiv  Detail & Related papers  (2024-10-24T16:32:23Z)
• On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning [71.55412580325743]
  We show that multi-task pretraining with fine-tuning on new tasks performs equally as well, or better, than meta-pretraining with meta test-time adaptation. This is encouraging for future research, as multi-task pretraining tends to be simpler and computationally cheaper than meta-RL.
  arXiv  Detail & Related papers  (2022-06-07T13:24:00Z)
• Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization [101.72755769194677]
  We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph. Our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks. Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks.
  arXiv  Detail & Related papers  (2022-05-25T10:44:25Z)
• Skill-based Meta-Reinforcement Learning [65.31995608339962]
  We devise a method that enables meta-learning on long-horizon, sparse-reward tasks. Our core idea is to leverage prior experience extracted from offline datasets during meta-learning.
  arXiv  Detail & Related papers  (2022-04-25T17:58:19Z)
• CoMPS: Continual Meta Policy Search [113.33157585319906]
  We develop a new continual meta-learning method to address challenges in sequential multi-task learning. We find that CoMPS outperforms prior continual learning and off-policy meta-reinforcement methods on several sequences of challenging continuous control tasks.
  arXiv  Detail & Related papers  (2021-12-08T18:53:08Z)
• Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling [126.69933134648541]
  We present a meta-reinforcement learning algorithm that is both efficient and extrapolates well when faced with out-of-distribution tasks at test time. Our method is based on a simple insight: we recognize that dynamics models can be adapted efficiently and consistently with off-policy data.
  arXiv  Detail & Related papers  (2020-06-12T13:34:46Z)
• Automated Relational Meta-learning [95.02216511235191]
  We propose an automated relational meta-learning framework that automatically extracts the cross-task relations and constructs the meta-knowledge graph. We conduct extensive experiments on 2D toy regression and few-shot image classification and the results demonstrate the superiority of ARML over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-01-03T07:02:25Z)

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.