Prioritized Experience Replay

Follow this topic Ask about this topic

Latest papers

10 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Correcting Within-Group Self-Selection Bias in Prioritized Replay
Sep 21, 2026Oscar Miró López-Feliu, Herke van HoofReinforcement Learning Prioritized Experience Replay
University of Amsterdam
Integrating Novelty and Surprise for Experience Prioritization and Exploration in Image-Based Reinforcement Learning
Aug 18, 2026Hoda Yamani, Henry Williams, Bruce A. MacDonaldPrioritized Experience Replay Reinforcement Learning
Robot Learning Team and CARES Robotics Lab, Department of Electrical, Computer, and Software Engineering, University of Auckland, Auckland, New Zealand.
Rollout-Level Advantage-Prioritized Experience Replay for GRPO
Jun 3, 2026Gyeongtae Yoo, Sanghyeok Park, Soohyuk Jang +2Sample-Efficient RL Group Relative Policy Optimization
Department of Electrical and Computer Engineering, Seoul National University · Interdisciplinary Program in AI, Seoul National University · AIIS, ASRI, INMC, and ISRC, Seoul National University
RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
May 31, 2026Yixiu Mao, Yun Qu, Qi Wang +2Reinforcement Learning RL for Language Model Reasoning
Department of Automation, Tsinghua University
Evolutionary Enhanced Multi-Agent Reinforcement Learning for Cooperative Air Combat
May 24, 2026Chengwei Li, Junlin Liu, Yang GaoMulti-Agent Coordination Reinforcement Learning
Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences
Replay-buffer engineering for noise-aware quantum circuit optimization
Apr 23, 2026Akash Kundu, Sebastian FeldQuantum Architecture Search Reinforcement Learning
Delft University of Technology, Delft, The Netherlands · Quantum Computing Division, QuTech, The Netherlands
Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning
Apr 18, 2026Weiyu Ma, Yongcheng Zeng, Yan Song +4Reinforcement Learning RL Post-Training
King Abdullah University of Science and Technology (KAUST) · Chinese Academy of Sciences, Institute of Automation (CASIA) · AI Centre, Department of Computer Science, University College London +1
D-SPEAR: Dual-Stream Prioritized Experience Adaptive Replay for Stable Reinforcement Learning in Robotic Manipulation
Mar 28, 2026Yu Zhang, Karl MasonPrioritized Experience Replay Reinforcement Learning
School of Computer Science University of Galway Galway, Ireland
Freezing of Gait Prediction using Proactive Agent that Learns from Selected Experience and DDQN Algorithm
Mar 4, 2026Septian Enggar Sukmana, Sang Won Bae, Tomohiro ShibataPrioritized Experience Replay Parkinson's Disease
Kyushu Institute of Technology · Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Kitakyushu, Japan · Stevens Institute of Technology +1
VLM-Guided Experience Replay
Feb 2, 2026Elad Sharony, Tom Jurgenson, Orr Krupnik +2Reinforcement Learning Prioritized Experience Replay
Technion · ForSight Robotics · Nvidia Research

Sep 21, 2026J/K move · Enter open · S save

Correcting Within-Group Self-Selection Bias in Prioritized Replay

Oscar Miró López-Feliu, Herke van Hoof

University of Amsterdam

Reinforcement Learning Prioritized Experience Replay Sample-Efficient RL

Open paper AskPDF arXiv

Prioritized experience replay (PER) improves sample efficiency by replaying high-priority transitions, usually according to absolute temporal-difference error. In stochastic environments, PER can distort the distribution of realized outcomes replayed from transitions with the same state-action pair. We call this within-group self-selection. We quantify the resulting changes in within-group outcome frequencies and mean Bellman targets. We decompose PER into between-group allocation and conditional sibling selection, and derive fixed-buffer corrections that preserve current group-level priority mass: SAMPLE selects a group through PER and trains on a uniformly sampled sibling; AVG averages sibling Bellman targets; and MODEL samples from an empirical full-outcome model. In exact state-action environments with rare high-magnitude outcomes, sibling-aware replay improves learning efficiency over PER, although matched parameter sweeps show that tuning can narrow some gaps. In MinAtar, approximate VQ-VAE groups with SAMPLE mitigate degradation under mean-preserving reward tails in four of five games. Sibling-aware replay thus retains the focus on high-priority state-action regions while recovering their empirical outcome frequencies.