CoMetaPNS combines meta-learned neural surrogates with a continual Bayesian Gaussian Mixture Model to adapt cardiac electrophysiology simulations to new data while avoiding catastrophic forgetting.
A Deeper Look at Experience Replay
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Recently experience replay is widely used in various deep reinforcement learning (RL) algorithms, in this paper we rethink the utility of experience replay. It introduces a new hyper-parameter, the memory buffer size, which needs carefully tuning. However unfortunately the importance of this new hyper-parameter has been underestimated in the community for a long time. In this paper we did a systematic empirical study of experience replay under various function representations. We showcase that a large replay buffer can significantly hurt the performance. Moreover, we propose a simple O(1) method to remedy the negative influence of a large replay buffer. We showcase its utility in both simple grid world and challenging domains like Atari games.
years
2026 6representative citing papers
SODACER uses fast and slow buffers with adaptive clustering for experience replay in safe RL, integrated with CBFs and Sophia optimizer to achieve faster convergence and safety on nonlinear systems like HPV transmission.
A new meta-training algorithm, ELO, combines a failure-aware resume buffer with progressive expert supervision; its best learned optimizer, ELO-Celo2, outperforms AdamW on ImageNet and GPT-2 and matches Muon on language modeling.
Rollout-level advantage-prioritized experience replay for GRPO recycles high-advantage individual rollouts with age eviction and fresh-anchored batches to outperform standard GRPO on math benchmarks, with gains increasing with model size.
Physical Atari is a robust under-$1000 hardware platform combining a bearing-based robot arm, Atari controller actuator, screen renderer, and camera for real-time RL experiments directly on physical hardware.
AGMARL-DKS uses per-node multi-agent RL with GNN state representations and stress-aware lexicographical ordering to outperform the default Kubernetes scheduler on fault tolerance, utilization, and cost for batch and mission-critical workloads.
citing papers explorer
-
CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations
CoMetaPNS combines meta-learned neural surrogates with a continual Bayesian Gaussian Mixture Model to adapt cardiac electrophysiology simulations to new data while avoiding catastrophic forgetting.
-
Self-Organizing Dual-Buffer Adaptive Clustering Experience Replay (SODACER) for Safe Reinforcement Learning in Optimal Control
SODACER uses fast and slow buffers with adaptive clustering for experience replay in safe RL, integrated with CBFs and Sophia optimizer to achieve faster convergence and safety on nonlinear systems like HPV transmission.
-
Efficient Long-Horizon Learning for Learned Optimization
A new meta-training algorithm, ELO, combines a failure-aware resume buffer with progressive expert supervision; its best learned optimizer, ELO-Celo2, outperforms AdamW on ImageNet and GPT-2 and matches Muon on language modeling.
-
Rollout-Level Advantage-Prioritized Experience Replay for GRPO
Rollout-level advantage-prioritized experience replay for GRPO recycles high-advantage individual rollouts with age eviction and fresh-anchored batches to outperform standard GRPO on math benchmarks, with gains increasing with model size.
-
Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots
Physical Atari is a robust under-$1000 hardware platform combining a bearing-based robot arm, Atari controller actuator, screen renderer, and camera for real-time RL experiments directly on physical hardware.
-
AGMARL-DKS: An Adaptive Graph-Enhanced Multi-Agent Reinforcement Learning for Dynamic Kubernetes Scheduling
AGMARL-DKS uses per-node multi-agent RL with GNN state representations and stress-aware lexicographical ordering to outperform the default Kubernetes scheduler on fault tolerance, utilization, and cost for batch and mission-critical workloads.