Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model

• URL: http://arxiv.org/abs/2412.13630v1
• Date: Wed, 18 Dec 2024 09:06:16 GMT
• Title: Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
• Authors: Xiu Yuan, Tongzhou Mu, Stone Tao, Yunhao Fang, Mengke Zhang, Hao Su,
• Abstract summary: This paper explores improving offline-trained imitation learning models through online interactions with the environment.<n>We introduce Policy Decorator, which uses a model-agnostic residual policy to refine large imitation learning models during online interactions.
• Score: 17.299418356048495
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in robot learning have used imitation learning with large models and extensive demonstrations to develop effective policies. However, these models are often limited by the quantity, quality, and diversity of demonstrations. This paper explores improving offline-trained imitation learning models through online interactions with the environment. We introduce Policy Decorator, which uses a model-agnostic residual policy to refine large imitation learning models during online interactions. By implementing controlled exploration strategies, Policy Decorator enables stable, sample-efficient online learning. Our evaluation spans eight tasks across two benchmarks-ManiSkill and Adroit-and involves two state-of-the-art imitation learning models (Behavior Transformer and Diffusion Policy). The results show Policy Decorator effectively improves the offline-trained policies and preserves the smooth motion of imitation learning models, avoiding the erratic behaviors of pure RL policies. See our project page (https://policydecorator.github.io) for videos.

Related papers

• Dense Policy: Bidirectional Autoregressive Learning of Actions [51.60428100831717]
  This paper introduces a bidirectionally expanded learning approach, termed Dense Policy, to establish a new paradigm for autoregressive policies in action prediction. It employs a lightweight encoder-only architecture to iteratively unfold the action sequence from an initial single frame into the target sequence in a coarse-to-fine manner. Experiments validate that our dense policy has superior autoregressive learning capabilities and can surpass existing holistic generative policies.
  arXiv  Detail & Related papers  (2025-03-17T14:28:08Z)
• Differentiable Information Enhanced Model-Based Reinforcement Learning [48.820039382764]
  Differentiable environments have heralded new possibilities for learning control policies by offering rich differentiable information. Model-based reinforcement learning (MBRL) methods exhibit the potential to effectively harness the power of differentiable information for recovering the underlying physical dynamics. However, this presents two primary challenges: effectively utilizing differentiable information to 1) construct models with more accurate dynamic prediction and 2) enhance the stability of policy training.
  arXiv  Detail & Related papers  (2025-03-03T04:51:40Z)
• Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone [72.17534881026995]
  We develop an offline and online fine-tuning approach called policy-agnostic RL (PA-RL)<n>We show the first result that successfully fine-tunes OpenVLA, a 7B generalist robot policy, autonomously with Cal-QL, an online RL fine-tuning algorithm.
  arXiv  Detail & Related papers  (2024-12-09T17:28:03Z)
• Dreamitate: Real-World Visuomotor Policy Learning via Video Generation [49.03287909942888]
  We propose a visuomotor policy learning framework that fine-tunes a video diffusion model on human demonstrations of a given task. We generate an example of an execution of the task conditioned on images of a novel scene, and use this synthesized execution directly to control the robot.
  arXiv  Detail & Related papers  (2024-06-24T17:59:45Z)
• Dual policy as self-model for planning [71.73710074424511]
  We refer to the model used to simulate one's decisions as the agent's self-model. Inspired by current reinforcement learning approaches and neuroscience, we explore the benefits and limitations of using a distilled policy network as the self-model.
  arXiv  Detail & Related papers  (2023-06-07T13:58:45Z)
• Model-Based Reinforcement Learning with Multi-Task Offline Pretraining [59.82457030180094]
  We present a model-based RL method that learns to transfer potentially useful dynamics and action demonstrations from offline data to a novel task. The main idea is to use the world models not only as simulators for behavior learning but also as tools to measure the task relevance. We demonstrate the advantages of our approach compared with the state-of-the-art methods in Meta-World and DeepMind Control Suite.
  arXiv  Detail & Related papers  (2023-06-06T02:24:41Z)
• A Unified Framework for Alternating Offline Model Training and Policy Learning [62.19209005400561]
  In offline model-based reinforcement learning, we learn a dynamic model from historically collected data, and utilize the learned model and fixed datasets for policy learning. We develop an iterative offline MBRL framework, where we maximize a lower bound of the true expected return. With the proposed unified model-policy learning framework, we achieve competitive performance on a wide range of continuous-control offline reinforcement learning datasets.
  arXiv  Detail & Related papers  (2022-10-12T04:58:51Z)
• Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling [34.88897402357158]
  We show that due to the limited distributional expressivity of policy models, previous methods might still select unseen actions during training. We adopt a generative approach by decoupling the learned policy into two parts: an expressive generative behavior model and an action evaluation model. Our proposed method achieves competitive or superior performance compared with state-of-the-art offline RL methods.
  arXiv  Detail & Related papers  (2022-09-29T04:36:23Z)
• Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy [13.819070455425075]
  We learn a dynamics model that fits under the empirical state-action visitation distribution for all historical policies. We then propose a novel dynamics model learning method, named textitPolicy-adapted Dynamics Model Learning (PDML). Experiments on a range of continuous control environments in MuJoCo show that PDML achieves significant improvement in sample efficiency and higher performance combined with the state-of-the-art model-based RL methods.
  arXiv  Detail & Related papers  (2022-07-25T12:45:58Z)
• Model Generation with Provable Coverability for Offline Reinforcement Learning [14.333861814143718]
  offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization. But due to the limitation under the offline setting, the learned model could not mimic real dynamics well enough to support reliable out-of-distribution exploration. We propose an algorithm to generate models optimizing their coverage for the real dynamics.
  arXiv  Detail & Related papers  (2022-06-01T08:34:09Z)

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.