SOTAVerified

Policy Gradient Methods

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 382 papers

TitleStatusHype
Improving DAPO from a Mixed-Policy Perspective—0
Local Pairwise Distance Matching for Backpropagation-Free Reinforcement Learning—0
Solving Zero-Sum Convex Markov Games—0
Equivalence of stochastic and deterministic policy gradients—0
Enhanced DACER Algorithm with High Diffusion Efficiency—0
On Global Convergence Rates for Federated Policy Gradient under Heterogeneous Environment—0
Learning from Algorithm Feedback: One-Shot SAT Solver Guidance with GNNs—0
Policy Testing in Markov Decision Processes—0
Self-Evolving Curriculum for LLM Reasoning—0
KIPPO: Koopman-Inspired Proximal Policy Optimization—0
Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language ModelsCode3
Token-Efficient RL for LLM Reasoning—0
Evolutionary Policy Optimization—0
Hierarchical Policy-Gradient Reinforcement Learning for Multi-Agent Shepherding Control of Non-Cohesive TargetsCode0
Ordering-based Conditions for Global Convergence of Policy Gradient Methods—0
Analysis of On-policy Policy Gradient Methods under the Distribution Mismatch—0
Residual Policy Gradient: A Reward View of KL-regularized Objective—0
ROCM: RLHF on consistency models—0
Convergence Guarantees of Model-free Policy Gradient Methods for LQR with Stochastic DataCode0
SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin—0
A Self-Supervised Reinforcement Learning Approach for Fine-Tuning Large Language Models Using Cross-Attention Signals—0
Reevaluating Policy Gradient Methods for Imperfect-Information GamesCode1
Fine-Tuning Discrete Diffusion Models with Policy Gradient MethodsCode1
Computing and Learning Stationary Mean Field Equilibria with Scalar Interactions: Algorithms and Applications—0
Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation—0
Show:102550
← PrevPage 1 of 16Next →

No leaderboard results yet.