Research map / Reinforcement learning / Offline RL
Adaptive Policy Learning for Offline-to-Online Reinforcement 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 adaptive greedy updates on online data and conservative updates on offline data | GCQL · MuJoCo D4RL tasks, Total | normalized score: 691$\pm$63 -> 969$\pm$131 | Helped |
| Use adaptive greedy updates on online data and conservative updates on offline data | GCTD3BC · MuJoCo D4RL tasks, Total | normalized score: 717$\pm$33 -> 905$\pm$71 | Helped |
| Add the greedy updating strategy (ablation) | GCQL · Halfcheetah, worse-quality datasets | normalized score | Helped |
| Add the online buffer (ablation) | GCQL · Halfcheetah, worse-quality datasets | normalized score | Helped |
| Add the online buffer (ablation) | GCQL · Halfcheetah medium datasets | training stability | Helped |
| Increase initial offline training steps from 5e4 to 2e5 (ablation) | GCQL · Walker2d | normalized score | No clear effect |
| Vary the number of updating steps per iteration (ablation) | GCQL · Walker2d | normalized score | No clear effect |
| Use higher online-buffer sampling probability (ablation) | GCQL · Medium and medium-replay datasets | normalized score | Helped |
| Use lower online-buffer sampling probability (ablation) | GCQL · Random and other datasets | normalized score | Helped |
| Set online-buffer sampling probability to 0.5 (ablation) | GCQL · Medium and random datasets | normalized score | Helped |
Closest papers by meaning
- From Static Policies to Adaptive Priors in Offline Reinforcement Learning (NeurIPS 2026 · similarity 0.93)
- Bayesian Design Principles for Offline-to-Online Reinforcement Learning (ICML 2024 · similarity 0.91)
- A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning (AAAI 2024 · similarity 0.91)
- Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning (ICML 2024 · similarity 0.91)
- Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees (ICLR 2024 · similarity 0.91)
- Hybrid Reinforcement Learning from Offline Observation Alone (ICML 2024 · similarity 0.91)
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.