Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance

• URL: http://arxiv.org/abs/2409.03996v1
• Date: Fri, 6 Sep 2024 02:49:12 GMT
• Title: Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance
• Authors: RenMing Huang, Shaochong Liu, Yunqiang Pei, Peng Wang, Guoqing Wang, Yang Yang, Hengtao Shen,
• Abstract summary: We propose a novel subgoal guidance learning strategy. We develop a diffusion strategy-based high-level policy to generate reasonable subgoals as waypoints. We evaluate our method on complex robotic navigation and manipulation tasks.
• Score: 46.8322564551124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we address the challenging problem of long-horizon goal-reaching policy learning from non-expert, action-free observation data. Unlike fully labeled expert data, our data is more accessible and avoids the costly process of action labeling. Additionally, compared to online learning, which often involves aimless exploration, our data provides useful guidance for more efficient exploration. To achieve our goal, we propose a novel subgoal guidance learning strategy. The motivation behind this strategy is that long-horizon goals offer limited guidance for efficient exploration and accurate state transition. We develop a diffusion strategy-based high-level policy to generate reasonable subgoals as waypoints, preferring states that more easily lead to the final goal. Additionally, we learn state-goal value functions to encourage efficient subgoal reaching. These two components naturally integrate into the off-policy actor-critic framework, enabling efficient goal attainment through informative exploration. We evaluate our method on complex robotic navigation and manipulation tasks, demonstrating a significant performance advantage over existing methods. Our ablation study further shows that our method is robust to observation data with various corruptions.

Related papers

• HIQL: Offline Goal-Conditioned RL with Latent States as Actions [81.67963770528753]
  We propose a hierarchical algorithm for goal-conditioned RL from offline data. We show how this hierarchical decomposition makes our method robust to noise in the estimated value function. Our method can solve long-horizon tasks that stymie prior methods, can scale to high-dimensional image observations, and can readily make use of action-free data.
  arXiv  Detail & Related papers  (2023-07-22T00:17:36Z)
• Efficient Learning of High Level Plans from Play [57.29562823883257]
  We present Efficient Learning of High-Level Plans from Play (ELF-P), a framework for robotic learning that bridges motion planning and deep RL. We demonstrate that ELF-P has significantly better sample efficiency than relevant baselines over multiple realistic manipulation tasks.
  arXiv  Detail & Related papers  (2023-03-16T20:09:47Z)
• 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)
• Learning to Explore by Reinforcement over High-Level Options [0.0]
  We propose a new method which grants an agent two intertwined options of behaviors: "look-around" and "frontier navigation" In each timestep, an agent produces an option and a corresponding action according to the policy. We demonstrate the effectiveness of the proposed method on two publicly available 3D environment datasets.
  arXiv  Detail & Related papers  (2021-11-02T04:21:34Z)
• Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning [15.33496710690063]
  We propose goal-aware cross-entropy (GACE) loss, that can be utilized in a self-supervised way. We then devise goal-discriminative attention networks (GDAN) which utilize the goal-relevant information to focus on the given instruction.
  arXiv  Detail & Related papers  (2021-10-25T14:24:39Z)
• C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks [133.40619754674066]
  Goal-conditioned reinforcement learning can solve tasks in a wide range of domains, including navigation and manipulation. We propose the distant goal-reaching task by using search at training time to automatically generate intermediate states. E-step corresponds to planning an optimal sequence of waypoints using graph search, while the M-step aims to learn a goal-conditioned policy to reach those waypoints.
  arXiv  Detail & Related papers  (2021-10-22T22:05:31Z)
• C-Learning: Horizon-Aware Cumulative Accessibility Estimation [29.588146016880284]
  We introduce the concept of cumulative accessibility functions, which measure the reachability of a goal from a given state within a specified horizon. We show that these functions obey a recurrence relation, which enables learning from offline interactions. We evaluate our approach on a set of multi-goal discrete and continuous control tasks.
  arXiv  Detail & Related papers  (2020-11-24T20:34:31Z)
• Automatic Curriculum Learning through Value Disagreement [95.19299356298876]
  Continually solving new, unsolved tasks is the key to learning diverse behaviors. In the multi-task domain, where an agent needs to reach multiple goals, the choice of training goals can largely affect sample efficiency. We propose setting up an automatic curriculum for goals that the agent needs to solve. We evaluate our method across 13 multi-goal robotic tasks and 5 navigation tasks, and demonstrate performance gains over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-06-17T03:58:25Z)

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.