Ascent Conditions for Length-Normalized Single-Rollout Policy Updates
cs.LG
Submitted: 2026-10-10
Updated: 2026-10-10
Sources
- On the Impossibility of Unbiased and Length-Invariant Policy Optimization with Outcome Rewards
- Information Geometry and Evolutionary Game Theory
- On-Policy RL with Optimal Reward Baseline
- SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation
- Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
- Understanding R1-Zero-Like Training: A Critical Perspective
- Trust Region Masking for Long-Horizon LLM Reinforcement Learning
- Best Practice Critic Optimization
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- On KL-Regularized Policy Optimization
- Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective
- Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks