Research map / Reinforcement learning / MDPs and planning
Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
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 proxy variables and confounding bridge functions to estimate policy values | P3O · Confounded offline POMDPs | suboptimality | Helped |
| Construct coupled minimax confidence regions for bridge functions and optimize pessimistic policy values | P3O · Confounded offline POMDPs | suboptimality: \tilde{\mathcal{O}}(n^{-1/2}) | Helped |
| Use partial coverage of the optimal policy rather than uniform coverage of the policy class | P3O · Confounded offline POMDPs | suboptimality | Helped |
Closest papers by meaning
- A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch (NeurIPS 2024 · similarity 0.91)
- Information-Directed Pessimism for Offline Reinforcement Learning (ICML 2024 · similarity 0.91)
- Model-based Reinforcement Learning for Confounded POMDPs (ICML 2024 · similarity 0.91)
- Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding (ICLR 2024 · similarity 0.91)
- Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning (ICLR 2024 · similarity 0.90)
- Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning (ICLR 2024 · similarity 0.90)
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.