Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help?
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/DLR-RM/rl-baselines3-zoo
Sources
- Policy Gradient in Partially Observable Environments: Approximation and Convergence
- An Approximate Ascent Approach To Prove Convergence of PPO
- Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
- Adam: A Method for Stochastic Optimization
- PTR-PPO: Proximal Policy Optimization with Prioritized Trajectory Replay
- Policy Gradient with Active Importance Sampling
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- You May Not Need Ratio Clipping in PPO
- BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds
- Reinforcement Learning for LLM Post-Training: A Survey
- Sample Efficient Actor-Critic with Experience Replay
- Sample Efficient Policy Gradient Methods with Recursive Variance Reduction
- Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
- Stochastic Recursive Momentum for Policy Gradient Methods
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