Research map / Reinforcement learning / Policy gradient and actor-critic

Distributionally-Robust Policy Learning from Observational Data

NeurIPS 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Confounding-robust policy evaluation

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies distributionally-robust policy learning from observational binary-treatment data, aiming to find policies that perform well under distribution shift between training and deployment.

Problem

Standard policy learning from observational data optimizes empirical performance and can fail when the deployment distribution differs from the training distribution.

Approach

Formulates policy learning as distributionally-robust optimization over distributions near the observational data, targeting worst-case policy value under distribution shift. Full method details are not available from the abstract.

Closest papers by meaning

• Distributionally Robust Policy Learning under Concept Drifts (ICML 2025 · similarity 0.93)
• Distributionally Robust Policy Evaluation and Learning for Continuous Treatment with Observational Data (AAAI 2025 · similarity 0.91)
• Confounding-Robust Policy Improvement (NeurIPS 2018 · similarity 0.90)
• Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms (NeurIPS 2024 · similarity 0.88)
• Towards Safe Policy Learning under Partial Identifiability: A Causal Approach (AAAI 2024 · similarity 0.88)
• Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes (NeurIPS 2024 · similarity 0.87)