Research map / Reinforcement learning / MDPs and planning
PAC Reinforcement Learning for Predictive State Representations
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 optimistic planning with maximum-likelihood model estimation and targeted core-test trajectory collection | PSR online reinforcement learning · PSRs | cumulative regret: \mathcal{O}(\dps^2H^{\frac{7}{2}}|\mathcal{U}_{A}|^4|\mathcal{A}|^2K^{\frac{1}{2}}\alpha^{-3}\cdot\log(KH\ncov|\mathcal{ | Helped |
| Represent dynamics with observable predictive operators rather than requiring a latent-state model | CRANE · PSRs | sample complexity: 1/\epsilon^2\times\mathrm{poly}(\dps,|\mathcal{U}_{A}|,1/\alpha,\log\ncov,H,|\mathcal{A}|,\log|\mathcal{O}|,\log(1/\delt | Helped |
| Require α-regularity of the core matrices | PSR online learning · PSRs | minimum samples for a (1/2)-optimal policy: \Omega(\min\{\frac{1}{\alpha H},|\mathcal{A}|^{H-1}\}) | Mixed |
Closest papers by meaning
- Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings (ICML 2023 · similarity 0.93)
- Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning (ICML 2024 · similarity 0.90)
- Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight (ICLR 2024 · similarity 0.89)
- Model-based Reinforcement Learning for Confounded POMDPs (ICML 2024 · similarity 0.89)
- Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge (AAAI 2024 · similarity 0.89)
- Scalable Policy-Based RL Algorithms for POMDPs (NeurIPS 2025 · 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.