Research map / Reinforcement learning / Offline RL
An Optimal Online Method of Selecting Source Policies for 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 UCB1 to select source policies online and combine the selected policy with random actions | Q-learning with policy reuse · Grid-based robot navigation, target task Ω | average evaluation reward | Helped |
| Use online source-policy selection with a decreasing reuse probability | Q-learning with policy reuse · Grid-based robot navigation, randomly selected target tasks | average evaluation reward | Helped |
| Retain ε-greedy exploration as source-policy reuse decreases | Q-learning with policy reuse · Grid-based robot navigation, target task Ω′ with no useful source policy | average evaluation reward | No clear effect |
| Continue exploration rather than stopping when the greedy policy beats source-policy rewards | Q-learning with policy reuse · Grid-based robot navigation, target task Ω | source-policy selection frequency | Helped |
Closest papers by meaning
- Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning (NeurIPS 2026 · similarity 0.88)
- A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning (AAAI 2024 · similarity 0.87)
- Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning (ICML 2024 · similarity 0.87)
- Rethinking Optimal Transport in Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design (ICML 2024 · similarity 0.87)
- Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data (AAAI 2025 · similarity 0.86)
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.