Research map / Reinforcement learning / Visual and representation RL
Offline Meta Reinforcement Learning -- Identifiability Challenges and Effective Data Collection Strategies
Ron Dorfman, Idan Shenfeld, Aviv Tamar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| reduce data diversity: uniform to initial states excluding semi-circle (ablation) | BOReL · Ant-Semi-circle | average return: 171.8 -> 102.8 | Hurt |
| reduce data diversity: uniform to fixed initial position (ablation) | BOReL · Ant-Semi-circle | average return: 171.8 -> 99.2 | Hurt |
| add CQL to critic training, uniform data (ablation) | BOReL · Ant-Semi-circle | average return: 171.8 -> 176.0 | Improved |
| add CQL to critic training, excluding s.c. data (ablation) | BOReL · Ant-Semi-circle | average return: 102.8 -> 116.6 | Improved |
| add CQL to critic training, fixed-position data (ablation) | BOReL · Ant-Semi-circle | average return: 99.2 -> 112.4 | Improved |
| remove reward relabelling (ablation) | BOReL · domains with varying rewards | average reward | Hurt |
| remove policy replaying (ablation) | BOReL · domains with non-overlapping identifying states | average reward | Hurt |
| remove policy replaying (ablation) | BOReL · domains with overlapping identifying states | average reward | No clear effect |
Closest papers by meaning
- Offline Meta-Reinforcement Learning with Advantage Weighting (ICML 2021 · similarity 0.93)
- Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning (NeurIPS 2024 · similarity 0.91)
- Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning (ICLR 2025 · similarity 0.90)
- Bayesian Design Principles for Offline-to-Online Reinforcement Learning (ICML 2024 · similarity 0.89)
- Hybrid Reinforcement Learning from Offline Observation Alone (ICML 2024 · similarity 0.89)
- Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations (AAAI 2024 · similarity 0.89)
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.
