Cover Image

Policy Bifurcation in Safe Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zou, Wenjun, Lyu, Yao, Li, Jie, Yang, Yujie, Li, Shengbo Eben, Duan, Jingliang, Zhan, Xianyuan, Liu, Jingjing, Zhang, Yaqin, Li, Keqiang
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Feasible Policy Iteration for Safe Reinforcement Learning
by: Yang, Yujie, et al.
Published: (2023)

Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model
by: Zheng, Yinan, et al.
Published: (2024)

Conformal Symplectic Optimization for Stable Reinforcement Learning
by: Lyu, Yao, et al.
Published: (2024)

Exchange Policy Optimization Algorithm for Semi-Infinite Safe Reinforcement Learning
by: Zhang, Jiaming, et al.
Published: (2025)

Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning
by: Zhang, Jiaming, et al.
Published: (2026)

Distributional Soft Actor-Critic with Harmonic Gradient for Safe and Efficient Autonomous Driving in Multi-lane Scenarios
by: Zhang, Feihong, et al.
Published: (2025)

Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model
by: Guan, Yang, et al.
Published: (2021)

Predictive Lagrangian Optimization for Constrained Reinforcement Learning
by: Zhang, Tianqi, et al.
Published: (2025)

On the Equilibrium between Feasible Zone and Uncertain Model in Safe Exploration
by: Yang, Yujie, et al.
Published: (2026)

Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal Locomotion
by: Zheng, Ziang, et al.
Published: (2025)

Distributional Soft Actor-Critic with Diffusion Policy
by: Liu, Tong, et al.
Published: (2025)

Distributional Soft Actor-Critic with Three Refinements
by: Duan, Jingliang, et al.
Published: (2023)

Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
by: Zhan, Guojian, et al.
Published: (2025)

Real-Time Generative Policy via Langevin-Guided Flow Matching for Autonomous Driving
by: Zhu, Tianze, et al.
Published: (2026)

Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model
by: Gao, Zeyu, et al.
Published: (2022)

Rocket Landing Control with Random Annealing Jump Start Reinforcement Learning
by: Jiang, Yuxuan, et al.
Published: (2024)

Query-Policy Misalignment in Preference-Based Reinforcement Learning
by: Hu, Xiao, et al.
Published: (2023)

Off-policy Reinforcement Learning with Model-based Exploration Augmentation
by: Wang, Likun, et al.
Published: (2025)

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
by: Liu, Shiqi, et al.
Published: (2026)

Diffusion Actor-Critic with Entropy Regulator
by: Wang, Yinuo, et al.
Published: (2024)

A Spectral Revisit of the Distributional Bellman Operator under the Cramér Metric
by: Wang, Keru, et al.
Published: (2026)

Enhanced DACER Algorithm with High Diffusion Efficiency
by: Wang, Yinuo, et al.
Published: (2025)

Diffusion-Based Planning for Autonomous Driving with Flexible Guidance
by: Zheng, Yinan, et al.
Published: (2025)

Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies
by: Luo, Yu, et al.
Published: (2024)

The Feasibility Theory of Constrained Reinforcement Learning: A Tutorial Study
by: Yang, Yujie, et al.
Published: (2024)

Hierarchical End-to-End Autonomous Driving: Integrating BEV Perception with Deep Reinforcement Learning
by: Lu, Siyi, et al.
Published: (2024)

Hierarchical Feature-level Reverse Propagation for Post-Training Neural Networks
by: Ding, Ni, et al.
Published: (2025)

Zeroth-Order Actor-Critic: An Evolutionary Framework for Sequential Decision Problems
by: Lei, Yuheng, et al.
Published: (2022)

On the Stability of Datatic Control Systems
by: Yang, Yujie, et al.
Published: (2024)

Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation
by: Zhan, Guojian, et al.
Published: (2026)

On the Optimization Landscape of Observer-based Dynamic Linear Quadratic Control
by: Duan, Jingliang, et al.
Published: (2026)

Bootstrap Off-policy with World Model
by: Zhan, Guojian, et al.
Published: (2025)

DRARL: Disengagement-Reason-Augmented Reinforcement Learning for Efficient Improvement of Autonomous Driving Policy
by: Zhou, Weitao, et al.
Published: (2025)

Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning
by: Mao, Liyuan, et al.
Published: (2024)

Truncated Rectified Flow Policy for Reinforcement Learning with One-Step Sampling
by: Zhou, Xubin, et al.
Published: (2026)

Canonical Form of Datatic Description in Control Systems
by: Zhan, Guojian, et al.
Published: (2024)

Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning
by: Yao, Yihang, et al.
Published: (2023)

Controllability Test for Nonlinear Datatic Systems
by: Yang, Yujie, et al.
Published: (2024)

Unraveling the Hidden Dynamical Structure in Recurrent Neural Policies
by: Li, Jin, et al.
Published: (2026)

Natural Gradient Gaussian Approximation Filter on Lie Groups for Robot State Estimation
by: Zhang, Tianyi, et al.
Published: (2026)