experience-replay

Tag

Cards List
#experience-replay

Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning

arXiv cs.LG · 4d ago Cached

This paper presents a layer-wise information-theoretic framework for replay-based continual learning, decomposing the generalization gap into replay-induced representation drift and optimization-dependence terms, with refinements via Wasserstein relaxation and SGLD instantiation.

0 favorites 0 likes
#experience-replay

Attention-based Experience Replay Framework for Continual Learning of Agnostic Time Series Forecasting Models

arXiv cs.AI · 2026-07-24 Cached

This paper introduces a novel continual learning framework for time series forecasting that uses attention-guided experience replay to enable models to adapt to new data distributions while avoiding catastrophic forgetting, evaluated on benchmarks and real-world piezometric data.

0 favorites 0 likes
#experience-replay

Conversational Domain Adaptation of IndicTrans2 across 21 Indic Languages via Experience Replay and Model Soups

arXiv cs.CL · 2026-06-30 Cached

This paper adapts IndicTrans2-1B to conversational register across 21 Indic languages using experience replay and model souping, achieving conversational gains without sacrificing general-domain performance, though human evaluation shows the metric-based gains may not reflect perceived quality improvements.

0 favorites 0 likes
#experience-replay

CLaaS: Continual learning as a service for sample efficient online learning

arXiv cs.LG · 2026-06-05 Cached

CLaaS is a system for continual learning of LLM agents in deployment, using experience replay for sample-efficient online adaptation.

0 favorites 0 likes
#experience-replay

From Imitation to Interaction: Mastering Game of Schnapsen with Shallow Reinforcement Learning

arXiv cs.AI · 2026-05-19 Cached

This paper investigates whether shallow neural network agents can master the card game Schnapsen using reinforcement learning, outperforming a supervised imitation baseline and achieving competitive results against a strong search-based opponent.

0 favorites 0 likes
#experience-replay

Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning

arXiv cs.CL · 2026-04-21 Cached

FreshPER introduces a freshness-aware prioritized experience replay method for LLM/VLM reinforcement learning that addresses the 'priority staleness' problem by applying exponential age decay to stored priorities, enabling off-policy reuse of trajectories. Evaluated on eight agentic, reasoning, and math tasks, FreshPER significantly outperforms on-policy baselines with gains up to +367% on Sokoban.

0 favorites 0 likes
#experience-replay

Hindsight Experience Replay

OpenAI Blog · 2017-07-05 Cached

OpenAI presents Hindsight Experience Replay (HER), a technique enabling sample-efficient reinforcement learning from sparse binary rewards without complex reward engineering. It is demonstrated on robotic arm manipulation tasks including pushing, sliding, and pick-and-place, and validated on physical robots.

0 favorites 0 likes
← Back to home

Submit Feedback