Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Robot Learning

• URL: http://arxiv.org/abs/2411.12155v3
• Date: Sat, 01 Feb 2025 04:09:07 GMT
• Title: Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Robot Learning
• Authors: Younggyo Seo, Pieter Abbeel,
• Abstract summary: We introduce Coarse-to-fine Q-Network with Action Sequence (CQN-AS), a novel value-based reinforcement learning algorithm. We study our algorithm on 53 robotic tasks with sparse and dense rewards, as well as with and without demonstrations.
• Score: 62.3886343725955
• License:
• Abstract: In reinforcement learning (RL), we train a value function to understand the long-term consequence of executing a single action. However, the value of taking each action can be ambiguous in robotics as robot movements are typically the aggregate result of executing multiple small actions. Moreover, robotic training data often consists of noisy trajectories, in which each action is noisy but executing a series of actions results in a meaningful robot movement. This further makes it difficult for the value function to understand the effect of individual actions. To address this, we introduce Coarse-to-fine Q-Network with Action Sequence (CQN-AS), a novel value-based RL algorithm that learns a critic network that outputs Q-values over a sequence of actions, i.e., explicitly training the value function to learn the consequence of executing action sequences. We study our algorithm on 53 robotic tasks with sparse and dense rewards, as well as with and without demonstrations, from BiGym, HumanoidBench, and RLBench. We find that CQN-AS outperforms various baselines, in particular on humanoid control tasks.

Related papers

• FAST: Efficient Action Tokenization for Vision-Language-Action Models [98.15494168962563]
  We propose a new compression-based tokenization scheme for robot actions, based on the discrete cosine transform. Based on FAST, we release FAST+, a universal robot action tokenizer, trained on 1M real robot action trajectories.
  arXiv  Detail & Related papers  (2025-01-16T18:57:04Z)
• Autoregressive Action Sequence Learning for Robotic Manipulation [32.9580007141312]
  Existing autoregressive architectures generate end-effector waypoints sequentially as word tokens in language modeling. We extend causal transformers' single-token prediction to support predicting a variable number of tokens in a single step. We propose the Autoregressive Policy architecture, which solves manipulation tasks by generating hybrid action sequences.
  arXiv  Detail & Related papers  (2024-10-04T04:07:15Z)
• Offline Imitation Learning Through Graph Search and Retrieval [57.57306578140857]
  Imitation learning is a powerful machine learning algorithm for a robot to acquire manipulation skills. We propose GSR, a simple yet effective algorithm that learns from suboptimal demonstrations through Graph Search and Retrieval. GSR can achieve a 10% to 30% higher success rate and over 30% higher proficiency compared to baselines.
  arXiv  Detail & Related papers  (2024-07-22T06:12:21Z)
• SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation [62.58480650443393]
  Segment Anything (SAM) is a vision-foundation model for generalizable scene understanding and sequence imitation. We develop a novel multi-channel heatmap that enables the prediction of the action sequence in a single pass.
  arXiv  Detail & Related papers  (2024-05-30T00:32:51Z)
• Unsupervised Learning of Effective Actions in Robotics [0.9374652839580183]
  Current state-of-the-art action representations in robotics lack proper effect-driven learning of the robot's actions. We propose an unsupervised algorithm to discretize a continuous motion space and generate "action prototypes" We evaluate our method on a simulated stair-climbing reinforcement learning task.
  arXiv  Detail & Related papers  (2024-04-03T13:28:52Z)
• Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning [54.636562516974884]
  In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. In this work, we propose MEDAL++, a novel design for self-improving robotic systems. The robot autonomously practices the task by learning to both do and undo the task, simultaneously inferring the reward function from the demonstrations.
  arXiv  Detail & Related papers  (2023-03-02T18:51:38Z)
• Lifelong Robotic Reinforcement Learning by Retaining Experiences [61.79346922421323]
  Many multi-task reinforcement learning efforts assume the robot can collect data from all tasks at all times. In this work, we study a practical sequential multi-task RL problem motivated by the practical constraints of physical robotic systems. We derive an approach that effectively leverages the data and policies learned for previous tasks to cumulatively grow the robot's skill-set.
  arXiv  Detail & Related papers  (2021-09-19T18:00:51Z)
• SQUIRL: Robust and Efficient Learning from Video Demonstration of Long-Horizon Robotic Manipulation Tasks [8.756012472587601]
  Deep reinforcement learning (RL) can be used to learn complex manipulation tasks. RL requires the robot to collect a large amount of real-world experience. S SQUIRL performs a new but related long-horizon task robustly given only a single video demonstration.
  arXiv  Detail & Related papers  (2020-03-10T20:26:26Z)

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.