Saved in:
Bibliographic Details
Main Authors: Bian, Yuexin, Feng, Jie, Wang, Tao, Li, Yijiang, Gao, Sicun, Shi, Yuanyuan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.23075
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917235314917376
author Bian, Yuexin
Feng, Jie
Wang, Tao
Li, Yijiang
Gao, Sicun
Shi, Yuanyuan
author_facet Bian, Yuexin
Feng, Jie
Wang, Tao
Li, Yijiang
Gao, Sicun
Shi, Yuanyuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_23075
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RN-D: Discretized Categorical Actors with Regularized Networks for On-Policy Reinforcement Learning
Bian, Yuexin
Feng, Jie
Wang, Tao
Li, Yijiang
Gao, Sicun
Shi, Yuanyuan
Machine Learning
Robotics
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.
title RN-D: Discretized Categorical Actors with Regularized Networks for On-Policy Reinforcement Learning
topic Machine Learning
Robotics
url https://arxiv.org/abs/2601.23075