Cover Image

Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Sun, Mingfei
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bayesian Natural Gradient Fine-Tuning of CLIP Models via Kalman Filtering
by: Abdi, Hossein, et al.
Published: (2025)

Gradient Regularized Natural Gradients
by: Dash, Satya Prakash, et al.
Published: (2026)

Rank-1 Approximation of Inverse Fisher for Natural Policy Gradients in Deep Reinforcement Learning
by: Huo, Yingxiao, et al.
Published: (2026)

GRADE: Replacing Policy Gradients with Backpropagation for LLM Alignment
by: Nel, Lukas Abrie
Published: (2025)

Beyond Backpropagation: Optimization with Multi-Tangent Forward Gradients
by: Flügel, Katharina, et al.
Published: (2024)

Neural Network Verification with PyRAT
by: Lemesle, Augustin, et al.
Published: (2024)

Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients
by: Thrampoulidis, Christos, et al.
Published: (2025)

Generalized Euler Logarithm and its Applications in Machine Learning: Natural Gradient, Backpropagation, Generalized EG, Mirror Descent and OLPS
by: Cichocki, Andrzej
Published: (2025)

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps
by: Yang, Ningyuan, et al.
Published: (2025)

Towards Flash Thinking via Decoupled Advantage Policy Optimization
by: Tan, Zezhong, et al.
Published: (2025)

Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation
by: Choe, Jean Seong Bjorn, et al.
Published: (2024)

Practical Boolean Backpropagation
by: Golbert, Simon
Published: (2025)

ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning
by: Gao, Chen-Xiao, et al.
Published: (2023)

OPD+: Rethinking the Advantage Design for On-Policy Distillation
by: Zhao, Hanyang, et al.
Published: (2026)

RAT: Retrieval-Augmented Transformer for Click-Through Rate Prediction
by: Li, Yushen, et al.
Published: (2024)

Learning without Global Backpropagation via Synergistic Information Distillation
by: Ye, Chenhao, et al.
Published: (2025)

Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning
by: Zhang, Beining, et al.
Published: (2025)

Do Transformer World Models Give Better Policy Gradients?
by: Ma, Michel, et al.
Published: (2024)

Smooth Gate Functions for Soft Advantage Policy Optimization
by: Denisov, Egor, et al.
Published: (2026)

GPG: Generalized Policy Gradient Theorem for Transformer-based Policies
by: Mao, Hangyu, et al.
Published: (2025)

Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
by: Yang, Tong, et al.
Published: (2023)

Stable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation
by: Xu, Zihang, et al.
Published: (2026)

ABPT: Amended Backpropagation through Time with Partially Differentiable Rewards
by: Li, Fanxing, et al.
Published: (2025)

Vertical Symbolic Regression via Deep Policy Gradient
by: Jiang, Nan, et al.
Published: (2024)

Fast Explanations via Policy Gradient-Optimized Explainer
by: Pan, Deng, et al.
Published: (2024)

Backpropagation-Free Metropolis-Adjusted Langevin Algorithm
by: Cobb, Adam D., et al.
Published: (2025)

Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
by: Huang, Kai, et al.
Published: (2023)

Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
by: Nishimori, Soichiro, et al.
Published: (2026)

HKAN: Hierarchical Kolmogorov-Arnold Network without Backpropagation
by: Dudek, Grzegorz, et al.
Published: (2025)

Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
by: Panda, Ashwinee, et al.
Published: (2025)

Dynamic Spectral Backpropagation for Efficient Neural Network Training
by: Muthuraman, Mannmohan
Published: (2025)

Exploring the Performance of Perforated Backpropagation through Further Experiments
by: Brenner, Rorry, et al.
Published: (2025)

Learning General Policies with Policy Gradient Methods
by: Ståhlberg, Simon, et al.
Published: (2025)

RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors
by: Bai, Fengshuo, et al.
Published: (2024)

Direct Soft-Policy Sampling via Langevin Dynamics
by: Ki, Donghyeon, et al.
Published: (2026)

Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
by: Liu, Tenglong, et al.
Published: (2024)

Generalized Policy Gradient with History-Aware Decision Transformer for Reliable Routing over Graph Signals
by: Wei, Xing, et al.
Published: (2025)

Policy Gradient with Kernel Quadrature
by: Hayakawa, Satoshi, et al.
Published: (2023)

Policy Gradient with Tree Expansion
by: Dalal, Gal, et al.
Published: (2023)

RAT-Bench: A Comprehensive Benchmark for Text Anonymization
by: Krčo, Nataša, et al.
Published: (2026)