Research map / Probabilistic and scientific modeling / Variational and generative sampling
Probabilistic Active Meta-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 |
|---|---|---|---|
| Select tasks using learned latent task embeddings instead of uniform sampling | PAML for cart-pole, pendubot, and cart-double-pole dynamics · Observed task parameters | NLL | Helped |
| Select tasks using learned latent task embeddings instead of uniform sampling | PAML for cart-pole, pendubot, and cart-double-pole dynamics · Observed task parameters | RMSE | Helped |
| Select tasks using learned latent task embeddings instead of Latin hypercube sampling | PAML for cart-pole, pendubot, and cart-double-pole dynamics · Observed task parameters | RMSE | Helped |
| Use latent task embeddings to select tasks when descriptors expose only pendulum length | PAML for cart-pole dynamics · Partially observed task parameters | Prediction error | Helped |
| Use latent task embeddings to select tasks when descriptors include an irrelevant noisy dimension | PAML for cart-pole dynamics · Noisy task parameters | NLL | Helped |
| Use latent task embeddings to select tasks when descriptors include an irrelevant noisy dimension | PAML for cart-pole dynamics · Noisy task parameters | RMSE | Helped |
| Select tasks from pixel descriptors using a learned latent representation | PAML for cart-pole dynamics · High-dimensional pixel task descriptors | NLL | Helped |
| Select tasks from pixel descriptors using a learned latent representation | PAML for cart-pole dynamics · High-dimensional pixel task descriptors | RMSE | Helped |
Closest papers by meaning
- Probabilistic Model-Agnostic Meta-Learning (NeurIPS 2018 · similarity 0.89)
- Skill-based Meta-Reinforcement Learning (ICLR 2022 · similarity 0.89)
- Active representation learning for general task space with applications in robotics (NeurIPS 2023 · similarity 0.88)
- More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms (ICML 2024 · similarity 0.88)
- Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills (AAAI 2024 · similarity 0.87)
- Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory (ICML 2018 · 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.