task representation
Context Shift Reduction for Offline Meta-Reinforcement Learning Y unkai Gao
Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks.
- Asia > China > Hong Kong (0.04)
- North America > United States > New York > Suffolk County > Stony Brook (0.04)
- Information Technology > Artificial Intelligence > Robots (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Artificial Intelligence > Natural Language (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
Neural Taskonomy: Inferring the Similarity of Task-Derived Representations from Brain Activity
Aria Wang, Michael Tarr, Leila Wehbe
Neural Information Processing Systems http://nips.cc/
- North America > United States > Pennsylvania > Allegheny County > Pittsburgh (0.05)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
Learning Task Specifications from Demonstrations
Marcell Vazquez-Chanlatte, Susmit Jha, Ashish Tiwari, Mark K. Ho, Sanjit Seshia
Neural Information Processing Systems http://nips.cc/
- North America > United States > California > Alameda County > Berkeley (0.04)
- North America > United States > Texas > Travis County > Austin (0.04)
- North America > United States > Illinois > Cook County > Chicago (0.04)
- North America > Canada > Quebec > Montreal (0.04)
TADAM: Task dependent adaptive metric for improved few-shot learning
Boris Oreshkin, Pau Rodríguez López, Alexandre Lacoste
Neural Information Processing Systems http://nips.cc/
- North America > Canada > Ontario > Toronto (0.14)
- North America > United States (0.04)
- North America > Canada > Quebec > Montreal (0.04)
- Europe > Spain (0.04)
Learning to Rank Pre-Trained Models Efficiently
With the top-ranked PTM candidates, we further learn to enrich task repr.
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
- North America > Canada > Ontario > Toronto (0.04)
- Europe > Ireland > Leinster > County Dublin > Dublin (0.04)
- (2 more...)
8989e07fc124e7a9bcbdebcc8ace2bc0-Paper.pdf
Meta-learning improvesgeneralization ofmachine learning models when faced with previously unseen tasks by leveraging experiences from different, yet related prior tasks.
- Europe > Germany > Baden-Württemberg > Tübingen Region > Tübingen (0.14)
- North America > United States > Massachusetts > Suffolk County > Boston (0.04)
- North America > United States > District of Columbia > Washington (0.04)
- (3 more...)
Supplemental Material: Meta-learning from Tasks with Heterogeneous Attribute Spaces
With NP, we used deep sets for handling tasks with heterogeneous attribute spaces. DS+FT (NP+FT) was the DS (NP) fine-tuned with each target dataset. The number of fine-tuning epochs was five. NP+FT, NP+MAML, and the proposed method. Results Table 2 shows the mean squared error for each target task.
- North America > Canada > Ontario > Toronto (0.14)
- North America > United States > Washington > King County > Seattle (0.04)
- North America > United States > Louisiana > Orleans Parish > New Orleans (0.04)
- (3 more...)