Hierarchical Semantic RL: Tackling the Problem of Dynamic Action Space for RL-based Recommendations

• URL: http://arxiv.org/abs/2510.09167v1
• Date: Fri, 10 Oct 2025 09:09:10 GMT
• Title: Hierarchical Semantic RL: Tackling the Problem of Dynamic Action Space for RL-based Recommendations
• Authors: Minmao Wang, Xingchen Liu, Shijie Yi, Likang Wu, Hongke Zhao, Fei Pan, Qingpeng Cai, Peng Jiang,
• Abstract summary: We introduce Hierarchical Semantic RL (HSRL), which reframes RL-based recommendation over a fixed Semantic Action Space (SAS)<n>HSRL encodes items as Semantic IDs (SIDs) for policy learning, and maps SIDs back to their original items via a fixed, invertible lookup during execution.<n>HSRL delivers an 18.421% CVR lift with only a 1.251% increase in cost, supporting HSRL as a scalable paradigm for RL-based recommendation.
• Score: 25.01398098265527
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recommender Systems (RS) are fundamental to modern online services. While most existing approaches optimize for short-term engagement, recent work has begun to explore reinforcement learning (RL) to model long-term user value. However, these efforts face significant challenges due to the vast, dynamic action spaces inherent in recommendation, which hinder stable policy learning. To resolve this bottleneck, we introduce Hierarchical Semantic RL (HSRL), which reframes RL-based recommendation over a fixed Semantic Action Space (SAS). HSRL encodes items as Semantic IDs (SIDs) for policy learning, and maps SIDs back to their original items via a fixed, invertible lookup during execution. To align decision-making with SID generation, the Hierarchical Policy Network (HPN) operates in a coarse-to-fine manner, employing hierarchical residual state modeling to refine each level's context from the previous level's residual, thereby stabilizing training and reducing representation-decision mismatch. In parallel, a Multi-level Critic (MLC) provides token-level value estimates, enabling fine-grained credit assignment. Across public benchmarks and a large-scale production dataset from a leading Chinese short-video advertising platform, HSRL consistently surpasses state-of-the-art baselines. In online deployment over a seven-day A/B testing, it delivers an 18.421% CVR lift with only a 1.251% increase in cost, supporting HSRL as a scalable paradigm for RL-based recommendation. Our code is released at https://github.com/MinmaoWang/HSRL.

Related papers

• RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization [65.23034604711489]
  We introduce RLoop, a self-improving framework for training large reasoning models.<n>RLoop transforms the standard training process into a virtuous cycle: it first uses RL to explore the solution space from a given policy, then filters the successful trajectories to create an expert dataset.<n>Our experiments show RLoops forgetting and substantially improves generalization, boosting average accuracy by 9% and pass@32 by over 15% compared to vanilla RL.
  arXiv  Detail & Related papers  (2025-11-06T11:27:16Z)
• Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments [3.905774454930983]
  Deep reinforcement learning achieves remarkable performance but lacks interpretability.<n> SILVER framework explains RL policy via Shapley-based regression but remains restricted to low-dimensional, binary-action domains.<n>We propose SILVER with RL-guided labeling, an enhanced variant that extends SILVER to multi-action and high-dimensional environments.
  arXiv  Detail & Related papers  (2025-10-22T05:04:43Z)
• ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertainty [28.291179179647795]
  We propose textbfAdaptive Rank Representation (AdaRL), a bi-level optimization framework that improves robustness.<n>At the lower level, AdaRL performs policy optimization under fixed-rank constraints with dynamics sampled from a Wasserstein ball around a centroid model.<n>At the upper level, it adaptively adjusts the rank to balance the bias--variance trade-off, projecting policy parameters onto a low-rank manifold.
  arXiv  Detail & Related papers  (2025-10-13T20:05:34Z)
• 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)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)
• Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL [29.885978495034703]
  offline reinforcement learning (RL) offers an appealing approach to real-world tasks by learning policies from pre-collected datasets. However, the performance of existing offline RL algorithms heavily depends on the scale and state-action space coverage of datasets. We provide a new insight that leveraging the fundamental symmetry of system dynamics can substantially enhance offline RL performance under small datasets.
  arXiv  Detail & Related papers  (2023-06-07T07:51:05Z)
• Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification [74.10976684469435]
  offline reinforcement learning (RL) algorithms can be transferred to multi-agent settings directly. We propose a simple yet effective method, Offline Multi-Agent RL with Actor Rectification (OMAR), to tackle this critical challenge. OMAR significantly outperforms strong baselines with state-of-the-art performance in multi-agent continuous control benchmarks.
  arXiv  Detail & Related papers  (2021-11-22T13:27:42Z)
• Value Penalized Q-Learning for Recommender Systems [30.704083806571074]
  Scaling reinforcement learning to recommender systems (RS) is promising since maximizing the expected cumulative rewards for RL agents meets the objective of RS. A key approach to this goal is offline RL, which aims to learn policies from logged data. We propose Value Penalized Q-learning (VPQ), an uncertainty-based offline RL algorithm.
  arXiv  Detail & Related papers  (2021-10-15T08:08:28Z)
• Critic Regularized Regression [70.8487887738354]
  We propose a novel offline RL algorithm to learn policies from data using a form of critic-regularized regression (CRR) We find that CRR performs surprisingly well and scales to tasks with high-dimensional state and action spaces.
  arXiv  Detail & Related papers  (2020-06-26T17:50:26Z)
• Conservative Q-Learning for Offline Reinforcement Learning [106.05582605650932]
  We show that CQL substantially outperforms existing offline RL methods, often learning policies that attain 2-5 times higher final return. We theoretically show that CQL produces a lower bound on the value of the current policy and that it can be incorporated into a policy learning procedure with theoretical improvement guarantees.
  arXiv  Detail & Related papers  (2020-06-08T17:53:42Z)
• MOPO: Model-based Offline Policy Optimization [183.6449600580806]
  offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. We show that an existing model-based RL algorithm already produces significant gains in the offline setting. We propose to modify the existing model-based RL methods by applying them with rewards artificially penalized by the uncertainty of the dynamics.
  arXiv  Detail & Related papers  (2020-05-27T08:46:41Z)

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.