Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning

• URL: http://arxiv.org/abs/2210.00350v1
• Date: Sat, 1 Oct 2022 19:31:46 GMT
• Title: Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning
• Authors: Zheng Wu, Yichen Xie, Wenzhao Lian, Changhao Wang, Yanjiang Guo, Jianyu Chen, Stefan Schaal and Masayoshi Tomizuka
• Abstract summary: In this work, we aim to achieve zero-shot policy generalization of Reinforcement Learning (RL) agents by leveraging the task compositionality. Our proposed method is a meta- RL algorithm with disentangled task representation, explicitly encoding different aspects of the tasks. Policy generalization is then performed by inferring unseen compositional task representations via the obtained disentanglement.
• Score: 30.633075584454275
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans are capable of abstracting various tasks as different combinations of multiple attributes. This perspective of compositionality is vital for human rapid learning and adaption since previous experiences from related tasks can be combined to generalize across novel compositional settings. In this work, we aim to achieve zero-shot policy generalization of Reinforcement Learning (RL) agents by leveraging the task compositionality. Our proposed method is a meta- RL algorithm with disentangled task representation, explicitly encoding different aspects of the tasks. Policy generalization is then performed by inferring unseen compositional task representations via the obtained disentanglement without extra exploration. The evaluation is conducted on three simulated tasks and a challenging real-world robotic insertion task. Experimental results demonstrate that our proposed method achieves policy generalization to unseen compositional tasks in a zero-shot manner.

Related papers

• Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills [17.666749042008178]
  We propose a framework called decoupled meta-reinforcement learning (DCMRL) DCMRL pulls in similar task contexts within the same task and pushing away different task contexts of different tasks. Experiments show that DCMRL is more effective than previous meta-RL methods with more generalizable prior experience.
  arXiv  Detail & Related papers  (2023-12-11T16:50:14Z)
• Towards Task Sampler Learning for Meta-Learning [37.02030832662183]
  Meta-learning aims to learn general knowledge with diverse training tasks conducted from limited data, and then transfer it to new tasks. It is commonly believed that increasing task diversity will enhance the generalization ability of meta-learning models. This paper challenges this view through empirical and theoretical analysis.
  arXiv  Detail & Related papers  (2023-07-18T01:53:18Z)
• Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts [75.75548749888029]
  We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks. With a single model, Musketeer achieves results comparable to or better than strong baselines trained on single tasks, almost uniformly across multiple tasks.
  arXiv  Detail & Related papers  (2023-05-11T17:57:49Z)
• Robust Subtask Learning for Compositional Generalization [20.54144051436337]
  We focus on the problem of training subtask policies in a way that they can be used to perform any task. We aim to maximize the worst-case performance over all tasks as opposed to the average-case performance.
  arXiv  Detail & Related papers  (2023-02-06T18:19:25Z)
• Continual Vision-based Reinforcement Learning with Group Symmetries [18.7526848176769]
  We introduce a unique Continual Vision-based Reinforcement Learning method that recognizes Group Symmetries, called COVERS. Our results show that COVERS accurately assigns tasks to their respective groups and significantly outperforms existing methods in terms of generalization capability.
  arXiv  Detail & Related papers  (2022-10-21T23:41:02Z)
• Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors [72.62423312645953]
  Humans intuitively solve tasks in versatile ways, varying their behavior in terms of trajectory-based planning and for individual steps. Current Imitation Learning algorithms often only consider unimodal expert demonstrations and act in a state-action-based setting. Instead, we combine a mixture of movement primitives with a distribution matching objective to learn versatile behaviors that match the expert's behavior and versatility.
  arXiv  Detail & Related papers  (2022-10-17T16:42:59Z)
• CompoSuite: A Compositional Reinforcement Learning Benchmark [20.89464587308586]
  We present CompoSuite, an open-source benchmark for compositional multi-task reinforcement learning (RL) Each CompoSuite task requires a particular robot arm to manipulate one individual object to achieve a task objective while avoiding an obstacle. We benchmark existing single-task, multi-task, and compositional learning algorithms on various training settings, and assess their capability to compositionally generalize to unseen tasks.
  arXiv  Detail & Related papers  (2022-07-08T22:01:52Z)
• 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)
• Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks [73.63892022944198]
  We present a generic perception architecture named Uni-Perceiver. It processes a variety of modalities and tasks with unified modeling and shared parameters. Results show that our pre-trained model without any tuning can achieve reasonable performance even on novel tasks.
  arXiv  Detail & Related papers  (2021-12-02T18:59:50Z)
• Variational Multi-Task Learning with Gumbel-Softmax Priors [105.22406384964144]
  Multi-task learning aims to explore task relatedness to improve individual tasks. We propose variational multi-task learning (VMTL), a general probabilistic inference framework for learning multiple related tasks.
  arXiv  Detail & Related papers  (2021-11-09T18:49:45Z)
• Meta-Learning with Fewer Tasks through Task Interpolation [67.03769747726666]
  Current meta-learning algorithms require a large number of meta-training tasks, which may not be accessible in real-world scenarios. By meta-learning with task gradient (MLTI), our approach effectively generates additional tasks by randomly sampling a pair of tasks and interpolating the corresponding features and labels. Empirically, in our experiments on eight datasets from diverse domains, we find that the proposed general MLTI framework is compatible with representative meta-learning algorithms and consistently outperforms other state-of-the-art strategies.
  arXiv  Detail & Related papers  (2021-06-04T20:15:34Z)

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.