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

• URL: http://arxiv.org/abs/2411.12155v5
• Date: Mon, 07 Jul 2025 19:21:42 GMT
• Title: Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Robot Learning
• Authors: Younggyo Seo, Pieter Abbeel,
• Abstract summary: We introduce a novel value-based reinforcement learning algorithm that learns a critic network that outputs Q-values over a sequence of actions.<n>Experiments show that CQN-AS outperforms several baselines on a variety of sparse-reward humanoid control and tabletop manipulation tasks.
• Score: 62.3886343725955
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Predicting a sequence of actions has been crucial in the success of recent behavior cloning algorithms in robotics. Can similar ideas improve reinforcement learning (RL)? We answer affirmatively by observing that incorporating action sequences when predicting ground-truth return-to-go leads to lower validation loss. Motivated by 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. Our experiments show that CQN-AS outperforms several baselines on a variety of sparse-reward humanoid control and tabletop manipulation tasks from BiGym and RLBench.

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)
• Continuous Control with Coarse-to-fine Reinforcement Learning [15.585706638252441]
  We present a framework that trains RL agents to zoom-into a continuous action space in a coarse-to-fine manner. We introduce a concrete, value-based algorithm within the framework called Coarse-to-fine Q-Network (CQN) CQN robustly learns to solve real-world manipulation tasks within a few minutes of online training.
  arXiv  Detail & Related papers  (2024-07-10T16:04:08Z)
• Strategically Conservative Q-Learning [89.17906766703763]
  offline reinforcement learning (RL) is a compelling paradigm to extend RL's practical utility. The major difficulty in offline RL is mitigating the impact of approximation errors when encountering out-of-distribution (OOD) actions. We propose a novel framework called Strategically Conservative Q-Learning (SCQ) that distinguishes between OOD data that is easy and hard to estimate.
  arXiv  Detail & Related papers  (2024-06-06T22:09:46Z)
• 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)
• Stop Regressing: Training Value Functions via Classification for Scalable Deep RL [109.44370201929246]
  We show that training value functions with categorical cross-entropy improves performance and scalability in a variety of domains. These include: single-task RL on Atari 2600 games with SoftMoEs, multi-task RL on Atari with large-scale ResNets, robotic manipulation with Q-transformers, playing Chess without search, and a language-agent Wordle task with high-capacity Transformers.
  arXiv  Detail & Related papers  (2024-03-06T18:55:47Z)
• Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning [19.4531905603925]
  i-QN is a principled approach that enables multiple consecutive Bellman updates by learning a tailored sequence of action-value functions.<n>We show that i-QN is theoretically grounded and that it can be seamlessly used in value-based and actor-critic methods.
  arXiv  Detail & Related papers  (2024-03-04T15:07:33Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world.<n>Recent methods aim to mitigate misalignment by learning reward functions from human preferences.<n>We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)
• 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)
• The impact of memory on learning sequence-to-sequence tasks [6.603326895384289]
  Recent success of neural networks in natural language processing has drawn renewed attention to learning sequence-to-sequence (seq2seq) tasks. We propose a model for a seq2seq task that has the advantage of providing explicit control over the degree of memory, or non-Markovianity, in the sequences.
  arXiv  Detail & Related papers  (2022-05-29T14:57:33Z)
• Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models [67.78935378952146]
  GenRL is a framework for solving sequential decision-making problems. It exploits the combination of reinforcement learning and latent variable generative models. We experimentally determine the characteristics of generative models that have most influence on the performance of the final policy training.
  arXiv  Detail & Related papers  (2022-04-18T22:02:32Z)
• Supervised Advantage Actor-Critic for Recommender Systems [76.7066594130961]
  We propose negative sampling strategy for training the RL component and combine it with supervised sequential learning. Based on sampled (negative) actions (items), we can calculate the "advantage" of a positive action over the average case. We instantiate SNQN and SA2C with four state-of-the-art sequential recommendation models and conduct experiments on two real-world datasets.
  arXiv  Detail & Related papers  (2021-11-05T12:51:15Z)
• Continuous Control with Action Quantization from Demonstrations [35.44893918778709]
  In Reinforcement Learning (RL), discrete actions, as opposed to continuous actions, result in less complex exploration problems. We propose a novel method: Action Quantization from Demonstrations (AQuaDem) to learn a discretization of continuous action spaces. We evaluate the proposed method on three different setups: RL with demonstrations, RL with play data --demonstrations of a human playing in an environment but not solving any specific task-- and Imitation Learning.
  arXiv  Detail & Related papers  (2021-10-19T17:59:04Z)
• 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)
• Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
  Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. We introduce a new RL formulation for text generation from the soft Q-learning perspective. We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
  arXiv  Detail & Related papers  (2021-06-14T18:48:40Z)
• Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention [67.1936055742498]
  We show that multi-task learning can effectively scale reset-free learning schemes to much more complex problems. This work shows the ability to learn dexterous manipulation behaviors in the real world with RL without any human intervention.
  arXiv  Detail & Related papers  (2021-04-22T17:38:27Z)
• A Framework for Efficient Robotic Manipulation [79.10407063260473]
  We show that a single robotic arm can learn sparse-reward manipulation policies from pixels. We show that, given only 10 demonstrations, a single robotic arm can learn sparse-reward manipulation policies from pixels.
  arXiv  Detail & Related papers  (2020-12-14T22:18:39Z)
• Parrot: Data-Driven Behavioral Priors for Reinforcement Learning [79.32403825036792]
  We propose a method for pre-training behavioral priors that can capture complex input-output relationships observed in successful trials. We show how this learned prior can be used for rapidly learning new tasks without impeding the RL agent's ability to try out novel behaviors.
  arXiv  Detail & Related papers  (2020-11-19T18:47:40Z)
• Learning Dexterous Manipulation from Suboptimal Experts [69.8017067648129]
  Relative Entropy Q-Learning (REQ) is a simple policy algorithm that combines ideas from successful offline and conventional RL algorithms. We show how REQ is also effective for general off-policy RL, offline RL, and RL from demonstrations.
  arXiv  Detail & Related papers  (2020-10-16T18:48:49Z)
• GRAC: Self-Guided and Self-Regularized Actor-Critic [24.268453994605512]
  We propose a self-regularized TD-learning method to address divergence without requiring a target network. We also propose a self-guided policy improvement method by combining policy-gradient with zero-order optimization. This makes learning more robust to local noise in the Q function approximation and guides the updates of our actor network. We evaluate GRAC on the suite of OpenAI gym tasks, achieving or outperforming state of the art in every environment tested.
  arXiv  Detail & Related papers  (2020-09-18T17:58:29Z)
• Probabilistic Active Meta-Learning [15.432006404678981]
  We introduce task selection based on prior experience into a meta-learning algorithm. We provide empirical evidence that our approach improves data-efficiency when compared to strong baselines on simulated robotic experiments.
  arXiv  Detail & Related papers  (2020-07-17T12:51:42Z)
• 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.