RN-D: Discretized Categorical Actors with Regularized Networks for On-Policy Reinforcement Learning

• URL: http://arxiv.org/abs/2601.23075v1
• Date: Fri, 30 Jan 2026 15:24:34 GMT
• Title: RN-D: Discretized Categorical Actors with Regularized Networks for On-Policy Reinforcement Learning
• Authors: Yuexin Bian, Jie Feng, Tao Wang, Yijiang Li, Sicun Gao, Yuanyuan Shi,
• Abstract summary: We revisit policy representation as a first-class design choice for on-policy optimization.<n>We study discretized categorical actors that represent each action dimension with a distribution over bins, yielding a policy objective that resembles a cross-entropy loss.<n>Our results show that simply replacing the standard actor network with our discretized regularized actor yields consistent gains.
• Score: 27.45103393884625
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: On-policy deep reinforcement learning remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy and policy updates must be conservative. In this paper, we revisit policy representation as a first-class design choice for on-policy optimization. We study discretized categorical actors that represent each action dimension with a distribution over bins, yielding a policy objective that resembles a cross-entropy loss. Building on architectural advances from supervised learning, we further propose regularized actor networks, while keeping critic design fixed. Our results show that simply replacing the standard actor network with our discretized regularized actor yields consistent gains and achieve the state-of-the-art performance across diverse continuous-control benchmarks.

Related papers

• Decentralized Learning Strategies for Estimation Error Minimization with Graph Neural Networks [86.99017195607077]
  We address real-time sampling and estimation of autoregressive Markovian sources in wireless networks.<n>We propose a graphical reinforcement learning framework for policy optimization.<n>Theoretically, our proposed policies are transferable, allowing a policy trained on one graph to be effectively applied to structurally similar graphs.
  arXiv  Detail & Related papers  (2026-01-19T02:18:45Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• Actor-Critic without Actor [4.94481688445056]
  We introduce Actor-Critic without Actor (ACA), a lightweight framework that eliminates the explicit actor network and instead generates actions directly from the field of a noise-level critic.<n>ACA achieves more favorable learning curves and competitive performance compared to both standard actor-critic and state-of-the-art diffusion-based methods.
  arXiv  Detail & Related papers  (2025-09-25T11:33:09Z)
• Value Improved Actor Critic Algorithms [5.301318117172143]
  We extend the standard framework of actor critic algorithms with value-improvement.<n>We prove that this approach converges in the popular analysis scheme of Generalized Policy Iteration.<n> Empirically, incorporating value-improvement into the popular off-policy actor-critic algorithms TD3 and SAC significantly improves or matches performance over their respective baselines.
  arXiv  Detail & Related papers  (2024-06-03T15:24:15Z)
• Time-Efficient Reinforcement Learning with Stochastic Stateful Policies [20.545058017790428]
  We present a novel approach for training stateful policies by decomposing the latter into a gradient internal state kernel and a stateless policy. We introduce different versions of the stateful policy gradient theorem, enabling us to easily instantiate stateful variants of popular reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2023-11-07T15:48:07Z)
• Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning [53.97273491846883]
  We propose DPE: an RL algorithm that blends offline sequence modeling and offline reinforcement learning with Double Policy Estimation. We validate our method in multiple tasks of OpenAI Gym with D4RL benchmarks.
  arXiv  Detail & Related papers  (2023-08-28T20:46:07Z)
• Offline Reinforcement Learning with Closed-Form Policy Improvement Operators [88.54210578912554]
  Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning. In this paper, we propose our closed-form policy improvement operators. We empirically demonstrate their effectiveness over state-of-the-art algorithms on the standard D4RL benchmark.
  arXiv  Detail & Related papers  (2022-11-29T06:29:26Z)
• Offline Reinforcement Learning with Soft Behavior Regularization [0.8937096931077437]
  In this work, we derive a new policy learning objective that can be used in the offline setting. Unlike state-independent regularization used in prior approaches, this textitsoft regularization allows more freedom of policy deviation. Our experimental results show that SBAC matches or outperforms the state-of-the-art on a set of continuous control locomotion and manipulation tasks.
  arXiv  Detail & Related papers  (2021-10-14T14:29:44Z)
• Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence [60.20076757208645]
  This paper proposes a general policy mirror descent (GPMD) algorithm for solving regularized RL. We demonstrate that our algorithm converges linearly over an entire range learning rates, in a dimension-free fashion, to the global solution.
  arXiv  Detail & Related papers  (2021-05-24T02:21:34Z)
• How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization [10.424426548124696]
  We propose MAGE, a model-based actor-critic algorithm, grounded in the theory of policy gradients. MAGE backpropagates through the learned dynamics to compute gradient targets in temporal difference learning. We demonstrate the efficiency of the algorithm in comparison to model-free and model-based state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-04-29T16:30:53Z)
• Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video [128.08590291947544]
  Temporally language grounding in untrimmed videos is a newly-raised task in video understanding. Inspired by human's coarse-to-fine decision-making paradigm, we formulate a novel Tree-Structured Policy based Progressive Reinforcement Learning framework.
  arXiv  Detail & Related papers  (2020-01-18T15:08:04Z)

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.