Research map / Bandits and online learning / RL theory and MDPs
Provable General Function Class Representation Learning in Multitask Bandits and MDP
Rui Lu, Andrew Zhao, Simon Shaolei Du, Gao Huang
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 |
|---|---|---|---|
| multitask training with M=5 and M=10 tasks sharing a CNN representation instead of single-task | GFUCB · neural-network contextual bandit (digit-value tasks) | cumulative regret | Improved |
| GFUCB (UCB-style confidence set) instead of eps-greedy at M=1 | GFUCB · neural-network contextual bandit, M=1 | cumulative regret | Improved |
| increase number of tasks M from 1 to 10 | GFUCB · neural-network contextual bandit | cumulative regret | Improved |
Closest papers by meaning
- Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits (ICML 2024 · similarity 0.86)
- Zero-Shot Reinforcement Learning via Function Encoders (ICML 2024 · similarity 0.86)
- Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples (ICML 2024 · similarity 0.85)
- Beyond task diversity: provable representation transfer for sequential multitask linear bandits (NeurIPS 2024 · similarity 0.85)
- The Non-linear $F$-Design and Applications to Interactive Learning (ICML 2024 · similarity 0.84)
- Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation (NeurIPS 2024 · similarity 0.84)
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.
