paper-with-me

Papers Policy Gradient Methods

“Policy Gradient Methods” 태그가 달린 논문 382편 · 필터 해제

Improving DAPO from a Mixed-Policy Perspective

2025-07-17 · Hongze Tan

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and…

Policy Gradient Methods

Local Pairwise Distance Matching for Backpropagation-Free Reinforcement Learning

2025-07-15 · Daniel Tanneberg

Training neural networks with reinforcement learning (RL) typically relies on backpropagation (BP), necessitating storage of activations from the forward pass for subsequent backward updates. Furthermore, backpropagating…

Policy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Solving Zero-Sum Convex Markov Games

2025-06-19 · Fivos Kalogiannis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Ian Gemp, Georgios Piliouras

We contribute the first provable guarantees of global convergence to Nash equilibria (NE) in two-player zero-sum convex Markov games (cMGs) by using independent policy gradient methods. Convex Markov games, recently defi…

Policy Gradient Methods

Equivalence of stochastic and deterministic policy gradients

2025-05-29 · Emo Todorov

Policy gradients in continuous control have been derived for both stochastic and deterministic policies. Here we study the relationship between the two. In a widely-used family of MDPs involving Gaussian control noise an…

continuous-controlContinuous ControlPolicy Gradient Methods

Enhanced DACER Algorithm with High Diffusion Efficiency

2025-05-29 · Yinuo Wang, Mining Tan, Wenjun Zou, Haotian Lin 외

Due to their expressive capacity, diffusion models have shown great promise in offline RL and imitation learning. Diffusion Actor-Critic with Entropy Regulator (DACER) extended this capability to online RL by using the r…

DenoisingImitation LearningMuJoCoOffline RL+1

On Global Convergence Rates for Federated Policy Gradient under Heterogeneous Environment

2025-05-29 · Safwan Labbi, Paul Mangold, Daniil Tiapkin, Eric Moulines

Ensuring convergence of policy gradient methods in federated reinforcement learning (FRL) under environment heterogeneity remains a major challenge. In this work, we first establish that heterogeneity, perhaps counter-in…

Federated LearningPolicy Gradient MethodsQ-Learning

Policy Testing in Markov Decision Processes

2025-05-21 · Kaito Ariu, Po-An Wang, Alexandre Proutiere, Kenshi Abe

We study the policy testing problem in discounted Markov decision processes (MDPs) under the fixed-confidence setting. The goal is to determine whether the value of a given policy exceeds a specified threshold while mini…

Policy Gradient Methods

Learning from Algorithm Feedback: One-Shot SAT Solver Guidance with GNNs

2025-05-21 · Jan Tönshoff, Martin Grohe

Boolean Satisfiability (SAT) solvers are foundational to computer science, yet their performance typically hinges on hand-crafted heuristics. This work introduces Reinforcement Learning from Algorithm Feedback (RLAF) as …

Combinatorial OptimizationPolicy Gradient Methodsreinforcement-learningReinforcement Learning

KIPPO: Koopman-Inspired Proximal Policy Optimization

2025-05-20 · Andrei Cozma, Landon Harris, Hairong Qi

Reinforcement Learning (RL) has made significant strides in various domains, and policy gradient methods like Proximal Policy Optimization (PPO) have gained popularity due to their balance in performance, training stabil…

Computational Efficiencycontinuous-controlContinuous ControlPolicy Gradient Methods+1

Self-Evolving Curriculum for LLM Reasoning

2025-05-20 · Xiaoyin Chen, Jiarui Lu, Minsu Kim, Dinghuai Zhang 외

Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influe…

Code GenerationPolicy Gradient MethodsReinforcement Learning (RL)

Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models

2025-05-05 · Zhengliang Shi, Lingyong Yan, Weiwei Sun, Yue Feng 외

Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG per…

Policy Gradient MethodsRAGRetrievalRetrieval-augmented Generation

Token-Efficient RL for LLM Reasoning

2025-04-29 · Alan Lee, Harry Tong

We propose reinforcement learning (RL) strategies tailored for reasoning in large language models (LLMs) under strict memory and compute limits, with a particular focus on compatibility with LoRA fine-tuning. Building on…

Policy Gradient MethodsReinforcement Learning (RL)

Evolutionary Policy Optimization

2025-04-17 · Zelal Su "Lain" Mustafaoglu, Keshav Pingali, Risto Miikkulainen

A key challenge in reinforcement learning (RL) is managing the exploration-exploitation trade-off without sacrificing sample efficiency. Policy gradient (PG) methods excel in exploitation through fine-grained, gradient-b…

Policy Gradient MethodsReinforcement Learning (RL)

Hierarchical Policy-Gradient Reinforcement Learning for Multi-Agent Shepherding Control of Non-Cohesive Targets

2025-04-03 · Stefano Covone, Italo Napolitano, Francesco De Lellis, Mario di Bernardo

We propose a decentralized reinforcement learning solution for multi-agent shepherding of non-cohesive targets using policy-gradient methods. Our architecture integrates target-selection with target-driving through Proxi…

Policy Gradient Methodsreinforcement-learningReinforcement Learning

Ordering-based Conditions for Global Convergence of Policy Gradient Methods

2025-04-02 · NeurIPS 2023 11 · Jincheng Mei, Bo Dai, Alekh Agarwal, Mohammad Ghavamzadeh 외

We prove that, for finite-arm bandits with linear function approximation, the global convergence of policy gradient (PG) methods depends on inter-related properties between the policy update and the representation. textc…

Policy Gradient Methods

Analysis of On-policy Policy Gradient Methods under the Distribution Mismatch

2025-03-28 · Weizhen Wang, Jianping He, Xiaoming Duan

Policy gradient methods are one of the most successful methods for solving challenging reinforcement learning problems. However, despite their empirical successes, many SOTA policy gradient algorithms for discounted prob…

Policy Gradient Methods

Residual Policy Gradient: A Reward View of KL-regularized Objective

2025-03-14 · Pengcheng Wang, Xinghao Zhu, Yuxin Chen, Chenfeng Xu 외

Reinforcement Learning and Imitation Learning have achieved widespread success in many domains but remain constrained during real-world deployment. One of the main issues is the additional requirements that were not cons…

Imitation LearningMuJoCoPolicy Gradient MethodsQ-Learning

ROCM: RLHF on consistency models

2025-03-08 · Shivanshu Shekhar, Tong Zhang

Diffusion models have revolutionized generative modeling in continuous domains like image, audio, and video synthesis. However, their iterative sampling process leads to slow generation and inefficient training, challeng…

Policy Gradient Methods

Convergence Guarantees of Model-free Policy Gradient Methods for LQR with Stochastic Data

2025-02-27 · Bowen Song, Andrea Iannelli

Policy gradient (PG) methods are the backbone of many reinforcement learning algorithms due to their good performance in policy optimization problems. As a gradient-based approach, PG methods typically rely on knowledge …

Policy Gradient Methods

SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin

2025-02-19 · Hao Yi, Qingyang Li, Yulan Hu, Fuzheng Zhang 외

Recently, enhancing the numerical and logical reasoning capability of Large Language Models (LLMs) has emerged as a research hotspot. Existing methods face several limitations: inference-phase techniques (e.g., Chain of …

GPULogical ReasoningPolicy Gradient MethodsReinforcement Learning (RL)+1
1–20 / 382 다음 →