Research map / Reinforcement learning / Visual and representation RL
Replay across Experiments: A Natural Extension of Off-Policy RL
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Replay across Experiments (RaE), reusing experience from prior experiments across multiple RL runs to improve controller performance and research iteration time.
Problem
Off-policy RL replay buffers are typically discarded after each experiment, wasting data that could aid stability, data efficiency, and iteration speed across experiments.
Approach
Extend replay beyond a single run by reusing experience collected in previous experiments as additional replay data in new experiments, with minimal changes to the standard off-policy RL workflow.
Experimental setup
Builds on: off-policy actor-critic experience replay
Closest papers by meaning
- Offline RL with Observation Histories: Analyzing and Improving Sample Complexity (ICLR 2024 · similarity 0.90)
- Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning (AAAI 2024 · similarity 0.89)
- Hybrid Reinforcement Learning from Offline Observation Alone (ICML 2024 · similarity 0.88)
- Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach (ICML 2025 · similarity 0.88)
- When Does Non-Uniform Replay Matter in Reinforcement Learning? (NeurIPS 2026 · similarity 0.88)
- A Clean Slate for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.