Research map / Continual learning / Online and replay-based
Selective Experience Replay for Lifelong Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DQN intersection policies instead of TTC | Intersection handling · Right, Left, Left2, Forward, Challenge | Avg. Time: 5.67s -> 4.70s; 6.98s -> 5.36s; 6.74s -> 6.48s; 6.44s -> 4.88s; 10.9s -> 6.83s | Helped |
| Use DQN intersection policies instead of TTC | Intersection handling · Right, Left2, Forward, Challenge | % Success: 98.7 -> 99.02; 82.7 -> 91.7; 94.5 -> 97.6; 65.0 -> 78.5 | Helped |
| Use DQN intersection policies instead of TTC | Intersection handling · Left | % Success: 96.03 -> 96.3 | No clear effect |
| Use DQN intersection policies instead of TTC | Intersection handling · All five scenarios | % Collisions: Right: 1.19 -> 0.96; Left: 3.30 -> 3.65; Left2: 16.7 -> 8.15; Forward: 4.7 -> 2.34; Challenge: 28.0 -> 21.4 | Mixed |
| Choose departure time with a Time-to-Go policy rather than requiring dynamic acceleration and deceleration | DQN intersection handling · Intersection scenarios | task completion time: %28 faster | Helped |
Closest papers by meaning
- Experience Replay for Continual Learning (NeurIPS 2019 · similarity 0.91)
- A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control (ICML 2025 · similarity 0.88)
- Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning (ICML 2024 · similarity 0.88)
- Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning (NeurIPS 2026 · similarity 0.87)
- Predicting the Susceptibility of Examples to Catastrophic Forgetting (ICML 2025 · similarity 0.87)
- Prioritized Generative Replay (ICLR 2025 · similarity 0.87)
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.