DEAS: DEtached value learning with Action Sequence for Scalable Offline RL

• URL: http://arxiv.org/abs/2510.07730v1
• Date: Thu, 09 Oct 2025 03:11:09 GMT
• Title: DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
• Authors: Changyeon Kim, Haeone Lee, Younggyo Seo, Kimin Lee, Yuke Zhu,
• Abstract summary: Action Sequence (DEAS) is a simple yet effective offline RL framework that leverages action sequences for value learning.<n>DEAS consistently outperforms baselines on complex, long-horizon tasks from OGBench.<n>It can be applied to enhance the performance of large-scale Vision-Language-Action models.
• Score: 46.40818333031899
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Offline reinforcement learning (RL) presents an attractive paradigm for training intelligent agents without expensive online interactions. However, current approaches still struggle with complex, long-horizon sequential decision making. In this work, we introduce DEtached value learning with Action Sequence (DEAS), a simple yet effective offline RL framework that leverages action sequences for value learning. These temporally extended actions provide richer information than single-step actions and can be interpreted through the options framework via semi-Markov decision process Q-learning, enabling reduction of the effective planning horizon by considering longer sequences at once. However, directly adopting such sequences in actor-critic algorithms introduces excessive value overestimation, which we address through detached value learning that steers value estimates toward in-distribution actions that achieve high return in the offline dataset. We demonstrate that DEAS consistently outperforms baselines on complex, long-horizon tasks from OGBench and can be applied to enhance the performance of large-scale Vision-Language-Action models that predict action sequences, significantly boosting performance in both RoboCasa Kitchen simulation tasks and real-world manipulation tasks.

Related papers

• Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning [61.380634253724594]
  Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL)<n>We show that it is possible to overcome this problem by acting and exploring within the internal representations of an autoregressive model.
  arXiv  Detail & Related papers  (2025-12-23T18:51:50Z)
• Reinforcement Learning with Action Chunking [56.838297900091426]
  We present Q-chunking, a recipe for improving reinforcement learning algorithms for long-horizon, sparse-reward tasks.<n>Our recipe is designed for the offline-to-online RL setting, where the goal is to leverage an offline prior dataset to maximize the sample-efficiency of online learning.<n>Our experimental results demonstrate that Q-chunking exhibits strong offline performance and online sample efficiency, outperforming prior best offline-to-online methods on a range of long-horizon, sparse-reward manipulation tasks.
  arXiv  Detail & Related papers  (2025-07-10T17:48:03Z)
• In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought [13.034968416139826]
  We propose an In-context Decision Transformer (IDT) to achieve self-improvement in a high-level trial-and-error manner. IDT is inspired by the efficient hierarchical structure of human decision-making. IDT achieves state-of-the-art in long-horizon tasks over current in-context RL methods.
  arXiv  Detail & Related papers  (2024-05-31T08:38:25Z)
• CUDC: A Curiosity-Driven Unsupervised Data Collection Method with Adaptive Temporal Distances for Offline Reinforcement Learning [62.58375643251612]
  We propose a Curiosity-driven Unsupervised Data Collection (CUDC) method to expand feature space using adaptive temporal distances for task-agnostic data collection. With this adaptive reachability mechanism in place, the feature representation can be diversified, and the agent can navigate itself to collect higher-quality data with curiosity. Empirically, CUDC surpasses existing unsupervised methods in efficiency and learning performance in various downstream offline RL tasks of the DeepMind control suite.
  arXiv  Detail & Related papers  (2023-12-19T14:26:23Z)
• Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning [68.16998247593209]
  offline reinforcement learning (RL) paradigm provides recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. In this paper, we propose an adaptive scheme for action quantization. We show that several state-of-the-art offline RL methods such as IQL, CQL, and BRAC improve in performance on benchmarks when combined with our proposed discretization scheme.
  arXiv  Detail & Related papers  (2023-10-18T06:07:10Z)
• TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning [73.53576440536682]
  We introduce TACO: Temporal Action-driven Contrastive Learning, a powerful temporal contrastive learning approach. TACO simultaneously learns a state and an action representation by optimizing the mutual information between representations of current states. For online RL, TACO achieves 40% performance boost after one million environment interaction steps.
  arXiv  Detail & Related papers  (2023-06-22T22:21:53Z)

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.